DEV Community: Romin Irani

[Boost]

Romin Irani — Fri, 12 Jun 2026 14:40:25 +0000

Aryan Irani for Google Developer Experts

Jun 12

Connecting GCP Budget Alerts to AppSheet: A Step-by-Step Guide

#googlecloud #appsheet #finops #cloudbilling

7 min read

Antigravity Managed Agents Tutorial: Ship Production AI Agents

Romin Irani — Tue, 09 Jun 2026 12:16:25 +0000

If you’ve tried building AI applications, you often face a familiar engineering wall.

It goes like this: You ask a Large Language Model to help you launch a website. It replies with beautiful code. But then what? The AI can’t actually open a text editor, save the file, or click “Run” to see if it works. You need to do all the heavy lifting.

You might say that you use one of the AI Agents that does a lot more including starting up the server, doing a few tests, etc. Of course they do but in case you had to do that, there are multiple things to consider:

Ensure that you do have a sandbox so the AI can run code safely without accidentally wiping your files.
Stitch together some logic of passing data back and forth across modules.
You need to configure tools, so that the AI can invoke those tools, talk to your data and/or even run a script.

There’s a lot more to think of and it all points towards more operational and management overheard to keep things running safely.

Here’s what this looks like in practice. Say you want an AI to write and test a Python script:

from google import genai
import subprocess

client = genai.Client()

# Step 1: Ask the model for code
response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents="Write a Python script that checks password strength and saves a report."
)

# Step 2: YOU must manually extract the code block from the text response
code = extract_code_from_markdown(response.text) # You wrote this function

# Step 3: YOU must save the file and run it locally
with open("password_checker.py", "w") as f:
    f.write(code)

# ⚠️ Danger: Running untrusted AI-generated code on YOUR machine!
result = subprocess.run(["python3", "password_checker.py"], capture_output=True, text=True)
print(result.stdout)

You’re doing all the work. The extraction. The file I/O. The risky local execution. The error loop when it inevitably fails.

What if you could replace all of this with a single API call?

What Are Managed Agents?

Google’s Managed Agents framework, featuring the flagship Antigravity agent, looks to help you overcome the engineering wall, that we just mentioned.

Think of it as Agent-as-a-Service. Instead of just giving you a text-based chatbot, Google instantly hands your AI its own secure, fully managed cloud computer (a Linux workspace) with the keys to the live internet.

Generated by NotebookLM for this article.

The Three Levels of AI Systems

Let’s look at the following table that highlights the three levels of AI Systems:

The Core Agentic Loop

When you give an Antigravity Agent a task, it doesn’t just guess an answer. It operates inside a continuous, hardware-backed loop:

┌────────────────────────────────────────┐
│ 1. PLAN & REASON │
│ (Analyzes objective & breaks it down) │
└───────────────────┬────────────────────┘
                    │
                    ▼
┌────────────────────────────────────────┐
│ 2. ACT │
│ (Executes a tool: Bash, Python, Web) │
└───────────────────┬────────────────────┘
                    │
                    ▼
┌────────────────────────────────────────┐
│ 3. OBSERVE │
│ (Reads execution output, errors, data) │
└───────────────────┬────────────────────┘
                    │
                    └─── Loop back until task is complete

This isn’t a one-shot prompt/response. The agent iterates. It writes a script, runs it, reads a SyntaxError from the terminal, fixes the bug, re-runs, and keeps going until the task is done.

The Remote Sandbox

Every time you invoke an Antigravity Agent, Google boots up a dedicated workspace:

What you get is a real Linux computer in the cloud that your agent owns for the duration of its task.

Architecture Deep Dive: How It All Works

When working with Managed Agents, you interact with two separate planes via the Gemini API:

                  ┌─────────────────────────────────┐
                  │ YOUR APP │
                  └────────┬───────────────┬────────┘
                           │ │
      1. Define/Configure │ │ 2. Run Task
      (System rules, ID) │ │ (Send Prompt)
                           ▼ ▼
 ┌───────────────────────────────────┐ ┌───────────────────────────────────┐
 │ THE CONTROL PLANE │ │ THE RUNTIME PLANE │
 │ (Agents API) │ │ (Interactions API) │
 ├───────────────────────────────────┤ ├───────────────────────────────────┤
 │ Saves persistent identity, system │ │ Spawns the Ubuntu sandbox, logs │
 │ instructions, and data mounts. │ │ live traces, and processes loops. │
 └───────────────────────────────────┘ └───────────────────────────────────┘

The Control Plane (Agents API) is where you configure and register your agent. Think of it as creating an employee profile i.e. you define its name, system instructions, custom skills, and code repositories to clone. It gives you back a static Agent ID.

The Runtime Plane (Interactions API) is where actual work happens. You send a task to your Agent ID via an “Interaction.” This plane handles sandbox provisioning, tool execution, reasoning traces, and the agentic loop.

Security: The Egress Proxy

Allowing an autonomous agent to run unverified scripts is a security risk. Google isolates the environment using an Egress Proxy Layer :

 ┌─────────────────────────┐
 │ REMOTE UBUNTU SANDBOX │
 │ (No internal secrets) │
 └───────────┬─────────────┘
             │ Agent attempts outbound API call
             ▼
 ┌─────────────────────────┐
 │ EGRESS PROXY LAYER │ ◄── Checks Domain Allowlist
 ├─────────────────────────┤
 │ Intercepts connection, │
 │ injects secrets securely│
 └───────────┬─────────────┘
             │ Safe, Authenticated Request Sent
             ▼
    [External Target API]

Three key guarantees:

Zero Secrets Inside the Sandbox. You never save API keys or database passwords in the agent’s Linux workspace.
Domain Allowlists. You explicitly define which external domains the agent can contact.
Header Transformations. When the agent needs to call an external API, the Egress Proxy intercepts the request, confirms the domain is allowed, and injects the authentication token automatically. The agent gets the data, but never sees your private key.

Getting Started: Your First Agent in 5 Minutes

Let’s create our First Agent using the Managed Agents framework.

Prerequisites

Before writing any code, make sure your environment meets these requirements:

Python: 3.10+. 3.12 recommended (matches sandbox runtime)
google-genai SDK >=2.0.0. The latest at the time of writing is 2.8.0.
API Key —Free tier available at aistudio.google.com/apikey.
OS : Any (macOS, Linux, Windows, or WSL). Your code runs locally, the agent runs in Google’s cloud.

python3 -m venv managed-agents-env
source managed-agents-env/bin/activate # On Windows: managed-agents-env\Scripts\activate
# Install (or upgrade) the Google GenAI SDK
pip install -U google-genai
# Verify the version — must be 1.14.0 or later
python3 -c "import google.genai; print(google.genai. __version__ )"
# Set your API key (get one at https://aistudio.google.com/apikey)
export GEMINI_API_KEY="your-api-key-here"

No local setup needed? You can also try Managed Agents directly in Google AI Studio without writing any code. Look for the “Managed Agents” template section. Iit gives you an interactive playground to test agent interactions in your browser.

Running the Examples

Every code block in this tutorial is a complete, self-contained Python script. To run any example:

# 1. Save the code to a file (an example name used here is hello_agent.py
vim hello_agent.py # or use any editor

# 2. Run it
python3 hello_agent.py

How long does it take? Each interaction takes 30 seconds to 3 minutes depending on task complexity. The agent is doing real work — booting a sandbox, writing code, executing it, reading errors, and iterating. Simple tasks finish in under a minute; complex multi-turn chains may take 2–3 minutes per turn.

Your First Interaction: Hello Managed Agents

Remember that painful multi-step code from earlier? Here’s the Antigravity Managed Agents equivalent:

from google import genai

client = genai.Client()

# One API call. One autonomous agent. One remote Linux sandbox.
interaction = client.interactions.create(
    agent="antigravity-preview-05-2026",
    input="Write a Python script that generates 100 random exam scores between 0 and 100, "
          "calculates the mean, median, and standard deviation, prints a summary, "
          "and saves a grade distribution histogram as grade_report.png using matplotlib.",
    environment="remote" # This provisions a secure Linux sandbox hosted by Google
)

print(interaction.output_text)

Run it:

python3 hello_agent.py

Expected output

For the first interaction, it produced the following output (your numbers will vary since the data is random):

I have successfully written and executed a Python script that generates 100 random exam scores, computes their key statistics, and plots a grade distribution histogram.

### 1. Generated Python Script (`generate_report.py`)

Here is the Python script, which is saved in the environment as `generate_report.py`. It uses `numpy` for data generation, `statistics` conventions for calculation (such as sample standard deviation), and `matplotlib` to generate a high-quality visualization.

python
import numpy as np
import matplotlib.pyplot as plt
import statistics

def generate_and_analyze_grades():
# Set a random seed for reproducibility
np.random.seed(42)

# Generate 100 random exam scores between 0 and 100 (inclusive)
scores = np.random.randint(0, 101, size=100)

# Calculate statistics using Python's standard statistics module and NumPy
# (Using ddof=1 for sample standard deviation, which is standard for student grade samples)
mean_val = np.mean(scores)
median_val = np.median(scores)
std_val = np.std(scores, ddof=1)

# Print summary to console
print("=========================================")
print(" EXAM GRADE REPORT SUMMARY ")
print("=========================================")
print(f"Number of Students : {len(scores)}")
print(f"Minimum Score : {np.min(scores)}")
print(f"Maximum Score : {np.max(scores)}")
print(f"Mean Score : {mean_val:.2f}")
print(f"Median Score : {median_val:.2f}")
print(f"Standard Deviation : {std_val:.2f}")
print("=========================================")

# Create the histogram plot
plt.figure(figsize=(10, 6))

# Customize the grid and style
plt.grid(axis='y', linestyle='--', alpha=0.7, zorder=0)

# Draw the histogram with bins of size 10 (0-10, 10-20, ..., 90-100)
bins = range(0, 111, 10)
plt.hist(scores, bins=bins, color='#4A90E2', edgecolor='black', rwidth=0.85, zorder=3)

# Add labels and title
plt.title('Distribution of Exam Scores', fontsize=16, fontweight='bold', pad=15)
plt.xlabel('Exam Scores', fontsize=12, labelpad=10)
plt.ylabel('Number of Students', fontsize=12, labelpad=10)

# Mark Mean and Median with vertical lines
plt.axvline(mean_val, color='#D0021B', linestyle='dashed', linewidth=2, zorder=4, label=f'Mean: {mean_val:.2f}')
plt.axvline(median_val, color='#F5A623', linestyle='dotted', linewidth=2, zorder=4, label=f'Median: {median_val:.2f}')

# Set x-ticks to align with bins
plt.xticks(range(0, 101, 10))

# Add a legend
plt.legend(fontsize=11, loc='upper left')

# Add details text box on the plot
textstr = '\n'.join((
    f'Total Students: {len(scores)}',
    f'Mean: {mean_val:.2f}',
    f'Median: {median_val:.2f}',
    f'Std Dev: {std_val:.2f}'
))
props = dict(boxstyle='round', facecolor='wheat', alpha=0.5)
plt.gca().text(0.05, 0.75, textstr, transform=plt.gca().transAxes, fontsize=10,
        verticalalignment='top', bbox=props)

# Adjust layout and save the figure
plt.tight_layout()
output_filename = 'grade_report.png'
plt.savefig(output_filename, dpi=300)
print(f"\nHistogram successfully saved to '{output_filename}'")

if name == ' main':
generate_and_analyze_grades()


---

### 2. Output Statistics Summary

Upon running the script in the sandbox environment, it produced the following output:

text

     EXAM GRADE REPORT SUMMARY

=========================================
Number of Students : 100
Minimum Score : 1
Maximum Score : 100
Mean Score : 51.31
Median Score : 53.50

Standard Deviation : 29.70

Histogram successfully saved to 'grade_report.png'


---

### 3. Generated Histogram Details (`grade_report.png`)

The script successfully outputted `grade_report.png` in high-resolution format (300 DPI) containing:
- **Clean Grid & Styling** : Standard light-gray horizontal grids to easily identify column heights.
- **Grade Bins** : Defined score ranges of size 10 (e.g., 0–10, 10–20, ..., 90–100) using custom spacing to give the columns a professional look.
- **Key Metrics Highlighted** : 
  - A red dashed line representing the **Mean** (`51.31`).
  - A yellow dotted line representing the **Median** (`53.50`).
- **An Info Legend and Box** : In the top-left area summarizing all descriptive statistics for easy offline reference.

### How to Run it Yourself
If you want to run this script in another environment, ensure you have the required packages installed:

bash
pip install matplotlib numpy
python generate_report.py

plaintext

📝 Note: The agent’s response is a natural-language summary, not raw program output. It describes what it did i.e. the code it wrote, the packages it installed, and the results. The actual Python script and chart file exist inside the remote sandbox.

That’s it. 3–4 lines of meaningful code that we can actually understand.

Behind the scenes, the agent:

Booted up an Ubuntu Linux sandbox
Wrote a Python script that generates random data and computes statistics
Auto-installed matplotlib (it wasn't asked to — it just knew it was needed)
Executed the script, rendering a histogram to grade_report.png
Returned a summary with the statistics and a confirmation that the chart was saved

Let’s try something more ambitious — a task that requires multiple tools:

from google import genai
client = genai.Client()

interaction = client.interactions.create(
    agent="antigravity-preview-05-2026",
    input="""
    Research the top 5 most popular Python web frameworks in 2026.
    For each framework:
    1. Find the latest version number and release date
    2. Count the GitHub stars
    3. Write a comparison table in Markdown
    """,
    environment="remote"
)

print(interaction.output_text)

plaintext

The agent will use web browsing to search Google, code execution to structure the data, and file management to save the results , all autonomously, all within one API call.

Here is the output:

The landscape of Python web development in **2026** is marked by a fascinating split [1, 2]. On one side, classic **backend-first** and **API-focused** frameworks (Django, FastAPI, Flask) remain the dominant standards for enterprise applications and microservices [3, 5]. On the other side, **pure-Python UI and full-stack** frameworks (Streamlit, Reflex) have seen explosive growth—driven by the need to build interactive web apps, data dashboards, and AI/ML interfaces without writing JavaScript or TypeScript [1, 2].

Below is an in-depth research report on the **top 5 most popular Python web frameworks in 2026** , ranked by GitHub stars and overall developer adoption.

---

### Detailed Breakdown of the Top 5 Python Web Frameworks

#### 1. FastAPI (99,034 GitHub Stars)
* **Latest Version:** `0.136.3` (Released: **May 23, 2026** )
* **Architecture Type:** ASGI (Asynchronous Server Gateway Interface)
* **Primary Focus:** High-Performance APIs and Microservices [4]
* **Core Philosophy:** FastAPI is designed to build APIs quickly with standard Python type hints. It leverages **Pydantic v2** for extremely fast data validation and serialization, and **Starlette** for high-concurrency async handling [3, 4]. It natively auto-generates interactive Swagger UI and ReDoc documentation.
* **Ideal Use Case:** AI/ML model deployment, backend APIs for single-page applications (React/Vue/Svelte), and low-latency microservices [5].

#### 2. Django (87,811 GitHub Stars)
* **Latest Version:** `6.0.6` (Released: **June 3, 2026** )
* **Architecture Type:** WSGI & ASGI (Fully async-supported)
* **Primary Focus:**"Batteries-Included" Monolithic Web Applications [4]
* **Core Philosophy:** As an 18-year industry standard, Django remains the premier full-featured web framework [2]. It handles everything—database routing (via its powerful ORM), administration panels, user authentication, form validation, and robust security defaults (SQLi, CSRF, XSS protection) [1]. In 2026, Django 6.x is highly optimized with full native asynchronous views and type hints [4].
* **Ideal Use Case:** Large-scale enterprise applications, content management systems, e-commerce platforms, and fast SaaS MVP development where you need a complete, secure architecture out of the box [2, 5].

#### 3. Flask (71,638 GitHub Stars)
* **Latest Version:** `3.1.3` (Released: **February 19, 2026** )
* **Architecture Type:** WSGI
* **Primary Focus:** Lightweight, Flexible Microframework [4]
* **Core Philosophy:** Flask provides a minimalist core, leaving the choice of database ORM, form handling, and security components completely up to the developer [1, 2]. Paired with modern 2026 extensions (SQLAlchemy 2.x, Pydantic), it represents a simple, un-opinionated foundation that never gets in the developer's way [3].
* **Ideal Use Case:** Small utility applications, lightweight APIs, microservices, and custom projects where developers want total control over their system design [1, 5].

#### 4. Streamlit (44,895 GitHub Stars)
* **Latest Version:** `1.58.0` (Released: **May 28, 2026** )
* **Architecture Type:** UI-First Scripting Paradigm
* **Primary Focus:** Rapid Data and Machine Learning Applications [1]
* **Core Philosophy:** Streamlit turns standard Python scripts into interactive, beautiful web apps in a matter of minutes. It handles the entire frontend and backend flow by re-running the script from top to bottom whenever a user interacts with a widget.
* **Ideal Use Case:** Quick data dashboards, machine learning model prototypes, and internal analytical tools for teams without frontend resources [1, 2].

#### 5. Reflex (28,467 GitHub Stars)
* **Latest Version:** `0.9.4` (Released: **June 4, 2026** )
* **Architecture Type:** Full-Stack Async React-Compiled
* **Primary Focus:** Interactive, Pure-Python Full-Stack Apps [2]
* **Core Philosophy:** Formerly known as Pynecone, Reflex compiles Python code into a high-performance **React/Next.js frontend** and a **FastAPI backend** , using real-time WebSockets to synchronize states between them [1, 2]. It bypasses JavaScript entirely, offering 60+ pre-built Radix UI components with native Tailwind integration [1, 2].
* **Ideal Use Case:** Complex, interactive web applications, real-time streaming dashboards (e.g., AI chat applications, financial trackers), and user-facing SaaS applications built entirely in Python [2].

---

### Other Honorable Mentions in 2026
While they didn't make the top 5 by GitHub stars, these frameworks are heavily utilized:
* **Tornado** (22,182 stars, v6.5.7, Released June 8, 2026): A mature, asynchronous networking framework ideal for long-lived WebSocket connections [4].
* **Sanic** (18,629 stars, v25.12.1, Released May 31, 2026): An ASGI web framework built for extreme speed and Flask-like simplicity, running on its own high-performance web server.
* **Litestar** (8,269 stars, v2.23.0, Released May 29, 2026): A highly structured, strict, and enterprise-grade ASGI alternative to FastAPI [3, 4].

---

### 2026 Python Web Frameworks Comparison Table

| Framework | GitHub Stars | Latest Version | Release Date | Architecture | Best For | Key Strength | Learning Curve |
| :--- | :--- | :--- | :--- | :--- | :--- | :--- | :--- |
| **FastAPI** | ~99,034 | `0.136.3` | May 23, 2026 | ASGI (Async) | High-performance API development & AI model deployments [4, 5] | Autogenerated Swagger docs, native Pydantic v2 validation [4] | **Easy / Moderate** |
| **Django** | ~87,811 | `6.0.6` | Jun 03, 2026 | WSGI / ASGI | Enterprise apps, content-heavy websites, secure SQL backends [1, 2] | "Batteries-included" (built-in admin, ORM, security, auth) [1, 2] | **Moderate / Hard** |
| **Flask** | ~71,638 | `3.1.3` | Feb 19, 2026 | WSGI (Sync-first) | Microservices, custom MVPs, lightweight apps [1, 5] | Unrivaled design flexibility, minimal core overhead [1] | **Very Easy** |
| **Streamlit** | ~44,895 | `1.58.0` | May 28, 2026 | Scripted Reactive | Data visualization dashboards & ML interactive tools [1] | Zero frontend experience needed; fast prototyping [1] | **Very Easy** |
| **Reflex** | ~28,467 | `0.9.4` | Jun 04, 2026 | Async React-compiled | Interactive, real-time SaaS & full-stack apps in pure Python [2] | True multi-page routing, state management without JavaScript [2] | **Moderate** |

---

### Guidance: Which Framework Should You Choose in 2026?

1. **Choose FastAPI** if you are building modern REST/GraphQL APIs, backend microservices, or deploying AI/ML models with high concurrency and automatic documentation [3, 5].
2. **Choose Django** if you are building database-driven business platforms or SaaS architectures where user authentication, administrative interfaces, and built-in security are paramount [1, 2].
3. **Choose Flask** if you need to build simple backend services or you want to hand-select every tool in your stack (e.g., combining custom database layers with external identity providers) [1].
4. **Choose Streamlit** if your core team consists of data scientists or business analysts who need to quickly present internal analytics, charts, and interactive widgets without building a complex web architecture [1, 2].
5. **Choose Reflex** if you want to build a fully interactive, production-ready full-stack application (with complex states, WebSocket interactions, and beautiful custom styles) but do not want to divide your team between Python and JavaScript [2].

---

### Sources & References
* [1] [Best Python Web Frameworks 2026 Compared - Reflex](https://reflex.dev/blog/top-python-web-frameworks/)
* [2] [Django vs Flask vs Reflex (April 2026) - Reflex](https://reflex.dev/blog/django-vs-flask-vs-reflex-comparison/)
* [3] [12 Modern Python Frameworks to Try in 2026 - Medium](https://medium.com/the-pythonworld/12-modern-python-frameworks-to-try-in-2026-e7089305bb19)
* [4] [5 top Python web frameworks of 2026 - Educative.io](https://www.educative.io/blog/top-python-web-frameworks)
* [5] [The Python Backend Framework Decision Guide for 2026 - Rollbar](https://rollbar.com/blog/python-backend-frameworks/)

plaintext

Multi-Turn Conversations: Persistent Sandbox State

What if you want the agent to build on its previous work? By default, each interactions.create() call spins up a brand-new, empty sandbox. To continue in the same environment, you pass two IDs back:

from google import genai
client = genai.Client()

# Turn 1: Research and create a report
interaction_1 = client.interactions.create(
    agent="antigravity-preview-05-2026",
    input="Research the current state of carbon capture technology in 2026. "
          "Write a comprehensive 500-word report and save it as report.md",
    environment="remote"
)
print(f"Environment ID: {interaction_1.environment_id}")
print(f"Interaction ID: {interaction_1.id}")
print(interaction_1.output_text)

# Turn 2: Build on the previous work - same sandbox, same files
interaction_2 = client.interactions.create(
    agent="antigravity-preview-05-2026",
    environment=interaction_1.environment_id, # ← Re-attaches to same Ubuntu sandbox
    previous_interaction_id=interaction_1.id, # ← Preserves conversation memory
    input="Convert that report.md file into a clean index.html webpage "
          "with modern inline CSS styling and responsive design."
          " Please output the contents of the index.html file"
)
print(interaction_2.output_text)

plaintext

The first interaction produced the report.md file.

Environment ID: 5eb9b4b8-c02f-4a8f-b7a0-c90a796c01a6
Interaction ID: v1_ChdidXNuYXJLQkF1eWlqdU1QODRmUjJRZxIXYnVzbmFyS0JBdXlpanVNUDg0ZlIyUWc
I have researched the state of carbon capture, utilization, and storage (CCUS)
technology in 2026 and compiled a comprehensive 494-word report. 
The report has been successfully saved to your environment as **`report.md`**.

Below is the full text of the report, 
highlighting how the CCUS sector has transitioned from pilot-stage 
demonstrations to industrial infrastructure in 2026.

***

# The State of Carbon Capture Technology in 2026: From Pilot to Infrastructure

## Executive Summary
....

## Point-Source Capture: The Current Backbone
...

## Scaling Direct Air Capture (DAC)
... 

## Infrastructure, Transport, and Policy
...

## Key Challenges
...

***

### Sources Cited

* **[1] S&P Global:** [2026 CCUS: Navigating the tides of the great realignment](https://www.spglobal.com/energy/en/news-research/blog/energy-transition/041426-2026-ccus-navigating-the-tides-of-the-great-realignment) (April 2026)
* **[2] Carbon Herald:** [What's Next For Carbon Capture, Utilization & Storage (CCUS) In 2026](https://carbonherald.com/whats-next-for-carbon-capture-utilization-storage-ccus-in-2026/) (January 2026)
* **[3] Nature Tech Memos:** [Top 10 Carbon Capture Startups for Corporate Partnerships in 2026](https://www.naturetechmemos.com/p/top-10-carbon-capture-startups-for-corporate-partnerships-in-2026) (April 2026)
.....

plaintext

The second interaction continued with the previous environment and interaction, and asked it to produce an HTML version of it i.e. index.html. The instruction specifically asked for the HTML contents to be produced.

I have successfully converted your `report.md` file into a clean, modern, and highly responsive **`index.html`** webpage! 

### What was done:
1. **Designed a cohesive palette:** Implemented a modern climate-tech inspired aesthetic using Slate (`#1e293b`) and a range of deep and light teals (`#0f766e`, `#14b8a6`, `#115e59`).
2. **Added an Interactive Stat Dashboard:** Created a high-level statistical summary card grid displaying key 2026 data at a glance (e.g., global Mtpa capacity, Stratos targets, US Section 45Q tax credits).
3. **Structured visual highlights:** Embedded two distinct grid comparison cards for the **Climeworks Mammoth** and **1PointFive Stratos** facilities, as well as a custom callout block highlighting the trans-European **Northern Lights** shipping route.
4. **Professionalized the typography & chemistry:** Used system-ui fonts for excellent loading speeds and correctly formatted all chemical formulas to standard subscripts (e.g., **CO<sub>2</sub>** ).
5. **Citations & Interactivity:** Mapped the original references into clickable, superscript citation numbers (e.g., `[1]`) that link smoothly down to a beautifully bulleted "Sources Cited" section with custom index bullet styling.

The full HTML contents of the newly created `index.html` are shown below:

html
<!DOCTYPE html>

The State of Carbon Capture Technology in 2026
 :root { --primary: #0f766e; --primary-light: #14b8a6; --primary-dark: #115e59; --bg: #f8fafc; --card-bg: #ffffff; --text-main: #1e293b; --text-muted: #475569; --accent: #0284c7; --border: #e2e8f0; --shadow: 0 4px 6px -1px rgba(15, 118, 110, 0.05), 0 2px 4px -2px rgba(15, 118, 110, 0.05); --shadow-md: 0 10px 15px -3px rgba(15, 118, 110, 0.1), 0 4px 6px -4px rgba(15, 118, 110, 0.1); } * { box-sizing: border-box; } body { font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, Helvetica, Arial, sans-serif; background-color: var(--bg); color: var(--text-main); line-height: 1.8; margin: 0; padding: 0; -webkit-font-smoothing: antialiased; } header { background: linear-gradient(135deg, #0d5c56 0%, #0f766e 50%, #115e59 100%); color: white; padding: 5rem 2rem; text-align: center; position: relative; } header::after { content: ''; position: absolute; bottom: 0; left: 0; right: 0; height: 6px; background: linear-gradient(90deg, var(--primary-light), var(--accent)); } .header-content { max-width: 800px; margin: 0 auto; } header h1 { font-size: 2.75rem; font-weight: 800; margin: 0 0 1rem 0; letter-spacing: -0.025em; line-height: 1.2; } header p { font-size: 1.25rem; color: #ccfbf1; margin: 0 0 1.5rem 0; font-weight: 300; } .meta { font-size: 0.875rem; color: #99f6e4; text-transform: uppercase; letter-spacing: 0.125em; font-weight: 600; } main { max-width: 900px; margin: -3rem auto 4rem auto; padding: 0 1.5rem; position: relative; z-index: 10; } .stats-grid { display: grid; grid-template-columns: repeat(auto-fit, minmax(200px, 1fr)); gap: 1.5rem; margin-bottom: 3rem; } .stat-card { background: var(--card-bg); padding: 1.75rem 1.5rem; border-radius: 14px; box-shadow: var(--shadow); border: 1px solid var(--border); text-align: center; transition: transform 0.25s ease, box-shadow 0.25s ease; } .stat-card:hover { transform: translateY(-5px); box-shadow: var(--shadow-md); } .stat-num { font-size: 2.25rem; font-weight: 800; color: var(--primary); margin-bottom: 0.5rem; line-height: 1; } .stat-label { font-size: 0.875rem; color: var(--text-muted); font-weight: 600; text-transform: uppercase; letter-spacing: 0.05em; } .content-wrapper { background: var(--card-bg); padding: 4rem 3.5rem; border-radius: 20px; box-shadow: var(--shadow-md); border: 1px solid var(--border); } section { margin-bottom: 3.5rem; } section:last-of-type { margin-bottom: 0; } h2 { color: var(--primary-dark); font-size: 1.85rem; font-weight: 700; margin-top: 0; margin-bottom: 1.5rem; border-bottom: 2px solid #f1f5f9; padding-bottom: 0.75rem; } p { margin-top: 0; margin-bottom: 1.5rem; font-size: 1.1rem; color: #334155; text-align: justify; } .highlight-grid { display: grid; grid-template-columns: 1fr 1fr; gap: 1.5rem; margin: 2rem 0; } @media (max-width: 768px) { header h1 { font-size: 2.25rem; } .content-wrapper { padding: 2.5rem 1.5rem; } .highlight-grid { grid-template-columns: 1fr; } } .highlight-box { background: #f0fdfa; border: 1px solid #ccfbf1; padding: 1.5rem; border-radius: 12px; border-left: 5px solid var(--primary); } .highlight-box h4 { margin: 0 0 0.75rem 0; color: var(--primary-dark); font-size: 1.15rem; font-weight: 700; } .highlight-box p { margin: 0; font-size: 0.95rem; color: #0f766e; text-align: left; line-height: 1.6; } .callout { background: #f8fafc; border: 1px solid var(--border); border-left: 5px solid var(--accent); padding: 1.5rem; border-radius: 4px 12px 12px 4px; margin: 2rem 0; } .callout-title { font-weight: 700; color: #0369a1; margin-bottom: 0.5rem; font-size: 1.1rem; } .callout p { margin: 0; font-size: 1rem; color: #475569; text-align: left; } .citation-link { color: var(--primary); text-decoration: none; font-weight: 700; font-size: 0.85rem; padding: 0 2px; vertical-align: super; } .citation-link:hover { color: var(--accent); text-decoration: underline; } .sources-section { background: #f8fafc; border: 1px solid var(--border); margin-top: 4rem; padding: 2.5rem; border-radius: 14px; } .sources-section h3 { margin-top: 0; color: var(--primary-dark); font-size: 1.35rem; margin-bottom: 1.5rem; font-weight: 700; } .sources-list { list-style-type: none; padding: 0; margin: 0; } .sources-list li { margin-bottom: 1rem; font-size: 0.95rem; padding-left: 2rem; position: relative; line-height: 1.6; color: #475569; } .sources-list li::before { content: attr(data-index); color: var(--primary); position: absolute; left: 0; font-weight: 700; background: #ccfbf1; width: 24px; height: 24px; border-radius: 50%; display: flex; align-items: center; justify-content: center; font-size: 0.75rem; top: 2px; } .sources-list a { color: var(--primary-dark); text-decoration: none; font-weight: 600; transition: color 0.2s ease; } .sources-list a:hover { color: var(--accent); text-decoration: underline; } footer { text-align: center; color: var(--text-muted); font-size: 0.875rem; margin-top: 4rem; padding-top: 2rem; border-top: 1px solid var(--border); }

<header>
    <div class="header-content">
        <span class="meta">Special Intelligence Report</span>
        <h1>The State of Carbon Capture Technology in 2026</h1>
        <p>From Pilot to Infrastructure</p>
    </div>
</header>

<main>
    <!-- Key Metrics Dashboard -->
    <div class="stats-grid">
        <div class="stat-card">
            <div class="stat-num">~73 Mtpa</div>
            <div class="stat-label">Global Operational Capacity</div>
        </div>
        <div class="stat-card">
            <div class="stat-num">500k Tons</div>
            <div class="stat-label">Stratos DAC Annual Target</div>
        </div>
        <div class="stat-card">
            <div class="stat-num">Up to $180</div>
            <div class="stat-label">US 45Q Subsidy per Ton</div>
        </div>
        <div class="stat-card">
            <div class="stat-num">36,000 T</div>
            <div class="stat-label">Mammoth Iceland Capacity</div>
        </div>
    </div>

    <div class="content-wrapper">
        <!-- Executive Summary -->
        <section id="executive-summary">
            <h2>Executive Summary</h2>
            <p>
                In 2026, the Carbon Capture, Utilization, and Storage (CCUS) industry is undergoing an "industrial hardening" phase, transitioning decisively from demonstration-stage pilots to commercial-scale infrastructure<sup><a href="#ref-1" class="citation-link">[1]</a></sup>. Global operational capture capacity has reached approximately 73 million metric tons per annum (Mtpa) as of mid-2026, up from 50 Mtpa in early 2025<sup><a href="#ref-1" class="citation-link">[1]</a></sup><sup><a href="#ref-2" class="citation-link">[2]</a></sup>. This momentum is propelled by robust climate policies, corporate carbon-removal commitments, and the commissioning of megaton-scale facilities.
            </p>
        </section>

        <!-- Point-Source Capture -->
        <section id="point-source">
            <h2>Point-Source Capture: The Current Backbone</h2>
            <p>
                Point-source carbon capture remains the commercial backbone of CCUS<sup><a href="#ref-2" class="citation-link">[2]</a></sup>. Technologies deployed at industrial and energy facilities—such as cement, steel, chemicals, and refining—now represent the vast majority of active capture capacity. Post-combustion chemical absorption using amine-based solvents is the most widely deployed technology<sup><a href="#ref-2" class="citation-link">[2]</a></sup>. Companies like Carbon Upcycling Technologies are successfully integrating capture systems with utilization, converting captured carbon dioxide (CO<sub>2</sub>) into high-quality construction materials, turning emissions from cement manufacturers into a low-carbon concrete feedstock<sup><a href="#ref-3" class="citation-link">[3]</a></sup>.
            </p>
        </section>

        <!-- Scaling Direct Air Capture -->
        <section id="dac">
            <h2>Scaling Direct Air Capture (DAC)</h2>
            <p>
                Direct Air Capture is experiencing a dramatic scale-up<sup><a href="#ref-4" class="citation-link">[4]</a></sup>. Climeworks' "Mammoth" facility in Iceland, operational since May 2024, captures up to 36,000 tons of CO<sub>2</sub> annually, storing it permanently underground via Carbfix mineralization<sup><a href="#ref-4" class="citation-link">[4]</a></sup><sup><a href="#ref-5" class="citation-link">[5]</a></sup>. Meanwhile, 1PointFive's (a subsidiary of Occidental Petroleum) "Stratos" facility in Ector County, Texas, is entering active operation in 2026<sup><a href="#ref-4" class="citation-link">[4]</a></sup>. Designed to capture up to 500,000 tons of atmospheric CO<sub>2</sub> annually using liquid solvent technology licensed from Carbon Engineering, Stratos is currently the world’s largest DAC plant<sup><a href="#ref-4" class="citation-link">[4]</a></sup><sup><a href="#ref-6" class="citation-link">[6]</a></sup>. 
            </p>

            <div class="highlight-grid">
                <div class="highlight-box">
                    <h4>Climeworks: Mammoth (Iceland)</h4>
                    <p>Nameplate capacity of 36,000 tons/year. Relies on solid-sorbent collectors powered by clean geothermal energy with deep Carbfix basaltic storage.</p>
                </div>
                <div class="highlight-box">
                    <h4>1PointFive: Stratos (Texas)</h4>
                    <p>World's largest facility with 500,000 tons/year target. Employs liquid-solvent infrastructure designed for rapid regional scalability.</p>
                </div>
            </div>

            <p>
                Major technology firms (including Microsoft, Google, Meta, and Amazon) have signed multi-year offtake agreements for high-quality, durable carbon credits, paying between $200 and $300 per ton, though current baseline DAC capture costs remain high, between $400 and $1,000 per ton<sup><a href="#ref-3" class="citation-link">[3]</a></sup><sup><a href="#ref-7" class="citation-link">[7]</a></sup>.
            </p>
        </section>

        <!-- Infrastructure, Transport, and Policy -->
        <section id="infrastructure">
            <h2>Infrastructure, Transport, and Policy</h2>
            <p>
                The commercial viability of carbon capture relies heavily on dedicated transportation and storage networks<sup><a href="#ref-2" class="citation-link">[2]</a></sup>. In Europe, 2026 marks the active operation of Norway’s "Northern Lights" project, the world's first open-source CO<sub>2</sub> transport and storage network<sup><a href="#ref-8" class="citation-link">[8]</a></sup>. For example, Yara's flagship Sluiskil ammonia plant in the Netherlands is liquefying up to 800,000 tons of CO<sub>2</sub> annually to be shipped by Northern Lights for permanent undersea storage<sup><a href="#ref-8" class="citation-link">[8]</a></sup>. Concurrently, Denmark’s "Greensand" offshore storage initiative is beginning operations<sup><a href="#ref-2" class="citation-link">[2]</a></sup>. 
            </p>

            <div class="callout">
                <div class="callout-title">The Trans-European Shipping Pathway</div>
                <p>Northern Lights bridges emission-heavy inland industrial sites like Yara Sluiskil in the Netherlands directly with permanent injection storage wells beneath the North Sea seabed.</p>
            </div>

            <p>
                On the policy front, the sector is heavily anchored by government subsidies. In the United States, the Inflation Reduction Act’s (IRA) modified Section 45Q tax credit provides up to $180 per metric ton for DAC and $85 per metric ton for point-source capture<sup><a href="#ref-9" class="citation-link">[9]</a></sup>. In the European Union, the Net Zero Industry Act has accelerated cross-border transport approvals, providing regulatory certainty.
            </p>
        </section>

        <!-- Key Challenges -->
        <section id="challenges">
            <h2>Key Challenges</h2>
            <p>
                Despite rapid progress, critical bottlenecks persist. Chief among these is the high energy intensity of DAC, which requires 1.5 to 2.5 megawatt-hours (MWh) of zero-carbon energy per ton of captured CO<sub>2</sub><sup><a href="#ref-7" class="citation-link">[7]</a></sup>. Permitting delays for geologic injection wells—specifically the EPA’s rigorous Class VI permits in the United States—also restrict how fast captured carbon can be sequestered<sup><a href="#ref-4" class="citation-link">[4]</a></sup>. Overcoming these economic and infrastructure hurdles remains essential to achieving megaton targets by 2030.
            </p>
        </section>

        <!-- Sources Cited -->
        <div class="sources-section">
            <h3>Sources Cited</h3>
            <ul class="sources-list">
                <li id="ref-1" data-index="1"><strong>S&P Global:</strong> <a href="https://www.spglobal.com/energy/en/news-research/blog/energy-transition/041426-2026-ccus-navigating-the-tides-of-the-great-realignment" target="_blank">2026 CCUS: Navigating the tides of the great realignment</a> (April 2026)</li>
                <li id="ref-2" data-index="2"><strong>Carbon Herald:</strong> <a href="https://carbonherald.com/whats-next-for-carbon-capture-utilization-storage-ccus-in-2026/" target="_blank">What's Next For Carbon Capture, Utilization & Storage (CCUS) In 2026</a> (January 2026)</li>
                <li id="ref-3" data-index="3"><strong>Nature Tech Memos:</strong> <a href="https://www.naturetechmemos.com/p/top-10-carbon-capture-startups-for-corporate-partnerships-in-2026" target="_blank">Top 10 Carbon Capture Startups for Corporate Partnerships in 2026</a> (April 2026)</li>
                <li id="ref-4" data-index="4"><strong>Senken:</strong> <a href="https://www.senken.io/blog/top-direct-air-capture-carbon-removal-projects-buyers-guide" target="_blank">The Top 3 Direct Air Capture Carbon Removal Projects</a> (February 2026)</li>
                <li id="ref-5" data-index="5"><strong>Climeworks:</strong> <a href="https://climeworks.com/plant-mammoth" target="_blank">Mammoth: our newest direct air capture and storage facility</a> (May 2024)</li>
                <li id="ref-6" data-index="6"><strong>Carbon Credits:</strong> <a href="https://carboncredits.com/top-3-carbon-capture-leaders-to-drive-the-net-zero-race-in-2026/" target="_blank">Top 3 Carbon Capture Leaders to Drive the Net-Zero Race in 2026</a> (January 2026)</li>
                <li id="ref-7" data-index="7"><strong>Energy Solutions Intelligence:</strong> <a href="https://energy-solutions.co/articles/sub/carbon-capture-direct-air-dac-cost-analysis" target="_blank">Direct Air Capture in 2026: Cost, Scale, and Path to $200/tCO2</a> (January 2026)</li>
                <li id="ref-8" data-index="8"><strong>World Economic Forum:</strong> <a href="https://www.weforum.org/stories/2026/01/scale-carbon-capture-storage-climate-action/" target="_blank">How to scale carbon capture and storage for climate action</a> (January 2026)</li>
                <li id="ref-9" data-index="9"><strong>International Energy Agency (IEA):</strong> <a href="https://www.iea.org/policies/16255-inflation-reduction-act-2022-sec-13104-extension-and-modification-of-credit-for-carbon-oxide-sequestration" target="_blank">Inflation Reduction Act 2022: Sec. 13104 Extension and Modification of Credit for Carbon Oxide Sequestration</a> (February 2026)</li>
            </ul>
        </div>

        <footer>
            <p style="text-align: center; color: var(--text-muted); font-size: 0.875rem; margin: 0;">&copy; 2026 Carbon Capture Intelligence. Compiled June 2026.</p>
        </footer>
    </div>
</main>

plaintext

The rendered form of the report is shown here:

Understanding the Two IDs

It is important to understand the Two IDs and here is a table that breaks it down:

Tip: You can pass environment_id without previous_interaction_id to reuse the files and installed packages, but start a fresh conversation. This is useful when you want to "fork" the workspace with a new task.

Downloading files

The previous section demonstrated how we can use the instruction itself to specify it to output the file content that it generated. That is one way but maybe not the way that you may want. You would probably want to download the file directly from the sandbox. Let’s do that.

Shown below is the entire code listing that we saw in the previous multi-turn interaction to create markdown report and then a HTML version of it. Just that we are going to add some code at the end to download the entire environment snapshot as a tar file and then extract it in a local folder. This is currently what the Managed Agents Environment supports. Read the documentation here.

import os
import requests
import tarfile
from google import genai
client = genai.Client()

# Turn 1: Research and create a report
interaction_1 = client.interactions.create(
    agent="antigravity-preview-05-2026",
    input="Research the current state of carbon capture technology in 2026. "
          "Write a comprehensive 500-word report and save it as report.md",
    environment="remote"
)
print(f"Environment ID: {interaction_1.environment_id}")
print(f"Interaction ID: {interaction_1.id}")
print(interaction_1.output_text)

# Turn 2: Build on the previous work - same sandbox, same files
interaction_2 = client.interactions.create(
    agent="antigravity-preview-05-2026",
    environment=interaction_1.environment_id, # ← Re-attaches to same Ubuntu sandbox
    previous_interaction_id=interaction_1.id, # ← Preserves conversation memory
    input="Convert that report.md file into a clean index.html webpage "
          "with modern inline CSS styling and responsive design."
          " Please output the contents of the index.html file"
)
print(interaction_2.output_text)

env_id = interaction_2.environment_id
api_key = os.environ.get("GEMINI_API_KEY")

response = requests.get(
    f"https://generativelanguage.googleapis.com/v1beta/files/environment-{env_id}:download",
    params={"alt": "media"},
    headers={"x-goog-api-key": api_key},
    allow_redirects=True,
)

with open("snapshot_env.tar", "wb") as f:
    f.write(response.content)

os.makedirs("extracted_env_snapshot", exist_ok=True)
with tarfile.open("snapshot_env.tar") as tar:
    tar.extractall(path="extracted_env_snapshot")

plaintext

Currently, as of writing this article, there is no SDK and it is a direct REST call to get the environment snapshot.

Here is the output on my local machine after I run the above program:

Customizing Agents: Skills, Personas, and Configuration

Instead of cramming everything into a single prompt string, Antigravity uses a filesystem-native configuration system. When the sandbox boots up, it automatically looks for a hidden .agents/ directory:

📁 Your-Project-Directory/
└── 📁 .agents/
    ├── 📄 AGENTS.md ← Global system instructions (persona, rules, standards)
    └── 📁 skills/
        └── 📁 data-cleaner/
            └── 📄 SKILL.md ← Specific skill with step-by-step instructions

plaintext

AGENTS.md — The Agent’s Persona

This file contains the foundational rules, behavioral guardrails, and project-specific context for your agent. Think of it as a README that the agent reads before starting any task.

SKILL.md — Modular Expertise

Skills package domain-specific expertise into reusable, modular units. They use YAML frontmatter for metadata and Markdown for instructions:

---
name: data-cleaner
description: Use when the user needs to clean, normalize, or validate tabular data files.
---
# Data Cleaner
## When to Use
- User provides CSV, Excel, or JSON files that need cleaning
- Data has missing values, inconsistent formatting, or duplicate rows
## Steps
1. Load the data file using pandas
2. Profile the data: count nulls, duplicates, and type mismatches
3. Apply cleaning rules (fill nulls, normalize strings, deduplicate)
4. Save the cleaned output and generate a summary report

plaintext

The key insight is progressive disclosure : the agent only loads the full content of a SKILL.md when it determines the skill is relevant to the current task. At startup, it reads only the name and description from the frontmatter, keeping the context window clean.

Tip: If a skill isn’t triggering when you expect it to, the issue is almost always the description in the YAML frontmatter. Make it more specific about when the skill should activate.

Persistent Agent Creation

For production use, you can register a persistent agent configuration so you don’t repeat yourself. In other words, you can create a Named Agent with the Agents API.

Let’s see how to create a persistent agent using the same CSV Cleaner logic skill that we introduced in the previous section.

from google import genai

client = genai.Client()

# Register a reusable, named agent with the data-cleaner skill baked in
agent = client.agents.create(
    id="my-csv-cleaner",
    base_agent="antigravity-preview-05-2026",
    system_instruction="You are a data quality engineer. Always use pandas for data manipulation. "
                       "Always generate a before/after summary showing what changed.",
    base_environment={
        "type": "remote",
        "sources": [
            {
                "type": "inline",
                "target": ".agents/AGENTS.md",
                "content": (
                    "# Data Quality Agent\n\n"
                    "## Standards\n"
                    "- Never drop rows silently — log every removal with a reason\n"
                    "- Normalize all string columns to lowercase, stripped of whitespace\n"
                    "- Output cleaned files in UTF-8 CSV format\n"
                    "- Always print a summary table at the end\n"
                )
            },
            {
                "type": "inline",
                "target": ".agents/skills/data-cleaner/SKILL.md",
                "content": (
                    "---\n"
                    "name: data-cleaner\n"
                    "description: Use when the user needs to clean, normalize, or validate tabular data files.\n"
                    "---\n"
                    "# Data Cleaner\n\n"
                    "## When to Use\n"
                    "- User provides CSV, Excel, or JSON files that need cleaning\n"
                    "- Data has missing values, inconsistent formatting, or duplicate rows\n\n"
                    "## Steps\n"
                    "1. Load the data file using pandas\n"
                    "2. Profile the data: count nulls, duplicates, and type mismatches\n"
                    "3. Apply cleaning rules (fill nulls, normalize strings, deduplicate)\n"
                    "4. Save the cleaned output and generate a summary report\n"
                )
            }
        ]
    }
)

print(f"Agent created with ID: {agent.id}")

python

Create a file named create_csv_cleaner_agent.py with the above code and run it. This will create a persistent agent that you can refer to via its registered agent ID i.e. my-csv-cleaner.

Let’s put the agent to use. First up, create a file with a few messed up customer records in a CSV file named messy_customers.csv.

name,email,phone,country
John Smith,john@example.com,+14155551234,US
jane doe, JANE@EXAMPLE.COM ,4155559999,
John Smith,john@example.com,+14155551234,US
Bob Wilson,bob@@invalid,+442071234567,
María García,maria@test.com,+34612345678,Spain
  alice brown ,alice@example.com,,US
Charlie Lee,charlie@test.com,+61412345678,AU
jane doe,jane@example.com,+14155559999,

python

Now you can invoke this agent by ID anywhere in your app. Create a file named run_csv_cleaner_agent.py with the content given below.

from google import genai

client = genai.Client()

# Read your local CSV file
with open("messy_customers.csv", "r") as f:
    csv_content = f.read()

# Inject the file into the sandbox and tell the agent to clean it
interaction = client.interactions.create(
    agent="my-csv-cleaner",
    input="Clean the file at data/customers.csv. "
          "Remove duplicate rows by email (case-insensitive), "
          "standardize phone numbers to E.164 format, "
          "fill missing 'country' fields by looking up the phone country code, "
          "and flag any rows where the email format is invalid. "
          "Generate a before/after summary showing what changed.",
    environment={
        "type": "remote",
        "sources": [
            {
                "type": "inline",
                "target": "data/customers.csv", # ← Path inside the sandbox
                "content": csv_content # ← Your local file contents
            }
        ]
    }
)

print(interaction.output_text)

python

What’s happening in the above code: The sources array pre-loads files into the sandbox before the agent starts working. The agent sees data/customers.csv as a real file in its Linux filesystem — it doesn't know or care that you injected it from your local machine. This works for any file type: CSV, JSON, XML, Python scripts, config files, etc.

Notice how the prompt doesn’t mention pandas, UTF-8, or logging rules — all of that is already encoded in the AGENTS.md and SKILL.md that the named agent carries with it. The data-cleaner skill activates automatically because the task description matches the skill's description field.

A sample run of the above file is shown below:

I have successfully cleaned the customer dataset at `data/customers.csv` using Python and `pandas`. 

Below is a detailed report and before/after summary of the transformations applied.

---

### Summary of Transformations

1. **whitespace Trimming:** Stripped all leading and trailing whitespace from both column names and text values (e.g., ` alice brown ` became `alice brown`).
2. **Email Normalization & Validation:** 
   - Converted all email addresses to lowercase and trimmed whitespace.
   - Added a new column `email_invalid` (boolean) to flag emails with an invalid format.
   - Identified `bob@@invalid` as an invalid format (due to a duplicate `@` symbol and lack of a top-level domain).
3. **Phone Number Standardization:**
   - Standardized all valid phone numbers to the international **E.164** format using the `phonenumbers` library.
   - Converted `4155559999` (with a default US region fallback) to `+14155559999`.
   - Ignored the missing phone number for `alice brown` while leaving it empty.
4. **Country Code Lookup:**
   - Looked up and populated missing `country` values based on the telephone country code prefix.
   - Filled `jane doe`'s country as `US` (derived from prefix `+1`).
   - Filled `Bob Wilson`'s country as `GB` (derived from prefix `+44`).
   - Kept existing valid country entries (e.g., `Spain`, `US`, `AU`) intact.
5. **Deduplication:**
   - Removed duplicate rows by performing a case-insensitive match on the cleaned `email` column, keeping the first occurrence.
   - Safely removed the duplicate row for `john@example.com` (Row 3).
   - Safely removed the duplicate row for `jane@example.com` (Row 8).

---

### Before/After Summary

#### 1. Data Quality Metrics

| Metric | Before Clean | After Clean | Change Description |
| :--- | :---: | :---: | :--- |
| **Total Rows** | 8 | 6 | 2 duplicate rows were removed. |
| **Duplicates Removed** | 0 | 2 | Dropped rows 3 (`john@example.com`) and 8 (`jane@example.com`). |
| **Invalid Emails Flagged** | 0 | 1 | Flagged `bob@@invalid` as invalid (`email_invalid = True`). |
| **Standardized Phone Numbers** | 1 | 5 | All numbers formatted to E.164 (e.g., `4155559999` -> `+14155559999`). |
| **Filled Country Fields** | 5 | 6 | Filled 2 missing country values (`US` and `GB`) via phone prefix lookups. |

#### 2. Row-by-Row Comparison

Below is the row-by-row evolution from the raw file to the cleaned output:

| Row # | Name (Before) | Name (After) | Email (Before) | Email (After) | Phone (Before) | Phone (After) | Country (Before) | Country (After) | Email Invalid Flag | Action Taken / Status |
| :---: | :--- | :--- | :--- | :--- | :--- | :--- | :--- | :--- | :---: | :--- |
| **1** | `John Smith` | `John Smith` | `john@example.com` | `john@example.com` | `+14155551234` | `+14155551234` | `US` | `US` | `False` | Retained as first unique instance. |
| **2** | `jane doe` | `jane doe` | ` JANE@EXAMPLE.COM ` | `jane@example.com` | `4155559999` | `+14155559999` | *Missing* | `US` | `False` | Email normalized; Phone formatted to E.164; Country populated from `+1` prefix. |
| **3** | `John Smith` | — | `john@example.com` | — | `+14155551234` | — | `US` | — | — | **Removed** (Duplicate email). |
| **4** | `Bob Wilson` | `Bob Wilson` | `bob@@invalid` | `bob@@invalid` | `+442071234567` | `+442071234567` | *Missing* | `GB` | `True` | Country populated from `+44` prefix; Email flagged as invalid. |
| **5** | `María García` | `María García` | `maria@test.com` | `maria@test.com` | `+34612345678` | `+34612345678` | `Spain` | `Spain` | `False` | Retained; Email valid; Preserved existing country. |
| **6** | ` alice brown ` | `alice brown` | `alice@example.com` | `alice@example.com` | *Missing* | *Missing* | `US` | `US` | `False` | Name whitespace stripped; Phone left empty; Preserved existing country. |
| **7** | `Charlie Lee` | `Charlie Lee` | `charlie@test.com` | `charlie@test.com` | `+61412345678` | `+61412345678` | `AU` | `AU` | `False` | Retained; Email valid. |
| **8** | `jane doe` | — | `jane@example.com` | — | `+14155559999` | — | *Missing* | — | — | **Removed** (Duplicate email). |

---

### Cleaned Dataset Output

The cleaned data has been written back to `data/customers.csv` and contains the following records:

csv
name,email,phone,country,email_invalid
John Smith,john@example.com,+14155551234,US,False
jane doe,jane@example.com,+14155559999,US,False
Bob Wilson,bob@@invalid,+442071234567,GB,True
María García,maria@test.com,+34612345678,Spain,False
alice brown,alice@example.com,,US,False
Charlie Lee,charlie@test.com,+61412345678,AU,False

plaintext

Building Real-World Agents: A few Use Cases

Now that you understand the foundations, let’s build a few agents. Each one introduces new capabilities and patterns.

Use Case 1: Automated Code Refactoring & Test Fixing

The Problem: You have a Python project with outdated code and failing tests. A standard LLM gives you code snippets, but you still have to manually copy, paste, run tests, debug, and iterate.

The Antigravity Solution: The agent clones your code, runs the test suite, reads terminal errors, patches the code, and re-runs tests — looping until everything passes.

We are providing a repository here with buggy code. Take a look:

GitHub - rominirani/uc1-legacy-app: Managed Agents Sample App Repository with Bugs

Known Bugs to fix for the Agent

As per the repository and you can take a look at it too, there are 3 root-cause bugs across the codebase (causing 6 test failures):

utils.py — calculate_total() does arithmetic on a string tax_rate without converting to float.
utils.py — normalize_name() crashes on None input (no null check).
models.py — Invoice.summary() references self.total (method object) instead of self.total() (method call).

The Code

Let’s write our Agent that can fix this for us. Check out the instruction in detail below:

from google import genai
client = genai.Client()

system_instructions = """
You are an expert QA and Refactoring Engineer. Your workflow is:
1. Clone the target repository into the workspace
2. Install all dependencies from requirements.txt
3. Run the full pytest suite and capture all output
4. For each failing test:
   a. Read the error traceback carefully
   b. Open the source file causing the failure
   c. Diagnose the root cause
   d. Apply the minimal fix
5. Re-run pytest after each fix to confirm resolution
6. Continue until ALL tests pass (0 failures)
7. Generate a summary of every change you made
IMPORTANT: Make the minimal possible change to fix each test.
Do not refactor working code unnecessarily.
"""
interaction = client.interactions.create(
    agent="antigravity-preview-05-2026",
    system_instruction=system_instructions,
    input="""
    Clone this repository: https://github.com/rominirani/uc1-legacy-app
    Run the pytest suite to check for environment or code failures.
    Isolate the bugs causing test failures and fix them one by one.
    Keep running the tests until you achieve a 100% pass rate.
    When done, provide:
    1. A list of all files modified with a diff summary
    2. The final pytest output showing all tests passing
    3. Any dependency changes you had to make
    """,
    environment="remote"
)
print(interaction.output_text)

plaintext

Run it: Save the above as uc1_refactor.py and run:

python3 uc1_refactor.py

shell

Expected output:

I have successfully diagnosed and resolved all the issues causing test failures in the `uc1-legacy-app` repository. Below is a detailed summary of the findings, modifications, and the final test execution output.

---

### 1. Modified Files & Diff Summary

#### File: `src/models.py`
- **Issue** : In the `Invoice.summary()` method, the `self.total` method itself was passed to `format_currency()` as an object, instead of being invoked (`self.total()`). This led to a `TypeError` during format evaluation.
- **Fix** : Changed `self.total` to `self.total()`.
- **Diff Summary** :

diff
@@ -23,7 +23,7 @@ class Invoice:
"""Return a one-line summary of the invoice."""
from src.utils import format_currency, normalize_name
name = normalize_name(self.customer_name)

return f"Invoice {self.invoice_id}: {name} - {format_currency(self.total)}"
return f"Invoice {self.invoice_id}: {name} - {format_currency(self.total())}"


#### File: `src/utils.py`
- **Issues** :
1. **`calculate_total()`**: When `tax_rate` is received as a string, Python fails to perform multiplication of float/string (`TypeError: can't multiply sequence by non-int of type 'float'`).
2. **`normalize_name()`**: When passed a `None` value (common in CSV imports), the code raised `AttributeError: 'NoneType' object has no attribute 'strip'`.
- **Fixes** :
1. Explicitly cast `subtotal` and `tax_rate` to `float` prior to calculating the tax.
2. Add a safeguard to return an empty string (`""`) when `name` is `None`.
- **Diff Summary** :

diff
@@ -11,8 +11,10 @@ def calculate_total(subtotal, tax_rate):
Returns:
The total as a float rounded to 2 decimal places.
"""

tax = subtotal * tax_rate / 100
return round(subtotal + tax, 2)
subtotal_val = float(subtotal)
tax_rate_val = float(tax_rate)
tax = subtotal_val * tax_rate_val / 100
return round(subtotal_val + tax, 2)

def format_currency(amount):
@@ -36,6 +38,8 @@ def normalize_name(name):
Returns:
Cleaned, title-cased name.
"""

if name is None:
return "" return name.strip().title()


---

### 2. Dependency Changes
No additional packages or dependency changes were made. All required libraries from `requirements.txt` (consisting of `pytest>=7.0.0`) were successfully installed and utilized without modification.

---

### 3. Final Pytest Output
Running the full suite confirms that all 10 tests now pass:

plaintext
============================= test session starts ==============================
platform linux -- Python 3.12.3, pytest-9.0.3, pluggy-1.6.0
rootdir: /uc1-legacy-app
plugins: anyio-4.13.0
collected 10 items

tests/test_models.py .... [40%]
tests/test_utils.py ...... [100%]

============================== 10 passed in 0.02s ==============================

plaintext

What Happens Behind the Scenes

The agent autonomously:

Runs git clone in the sandbox terminal
Runs pip install -r requirements.txt (installing into the sandbox's Python)
Runs pytest -v and reads the full output, including tracebacks
Opens the failing source files, identifies buggy logic
Writes patches, saves files, re-runs pytest
Loops until the output shows 0 failures

Key Concept Introduced: The Plan → Act → Observe loop in action. The agent doesn’t just generate code — it executes, reads real terminal output, and self-corrects.

Use Case 2: Live Competitive Intelligence Engine

The Problem: You need a deep competitive analysis of rival products. Manual web scraping is tedious, and static scrapers break constantly.

The Antigravity Solution: The agent uses its web browsing tools to search Google, crawls competitor websites, dynamically adapts to different page structures, writes a custom pandas script to structure the data, and exports a polished spreadsheet.

The Code

from google import genai
client = genai.Client()

system_instructions = """
You are a precise Business Intelligence Analyst. Your workflow:
1. Use web search to find current, real-time information
2. Navigate to official product/pricing pages for each competitor
3. Extract: pricing tiers, key features, target audience, notable limitations
4. Structure ALL findings into a pandas DataFrame
5. Export to both CSV and a formatted Markdown comparison table
6. Include the date/time of research and source URLs for every data point
Rules:
- Only report data you can verify from official sources
- If pricing isn't publicly available, note "Contact Sales" - don't guess
- Use USD for all pricing normalization
"""
interaction = client.interactions.create(
    agent="antigravity-preview-05-2026",
    system_instruction=system_instructions,
    input="""
    Research the pricing models and core feature matrices of the top 3 alternative
    platforms to Vercel for frontend deployment:
    1. Netlify
    2. Cloudflare Pages
    3. Cloud Run
    For each, extract:
    - Free tier limits (bandwidth, builds, sites)
    - Pro/paid tier pricing and what it unlocks
    - Key differentiating features
    - Notable limitations or complaints from developer communities
    Create:
    1. A competitive_matrix.csv spreadsheet with all data
    2. A competitive_analysis.md report with a formatted comparison table
       and a "Recommendation" section at the bottom
    """,
    environment="remote"
)
print(interaction.output_text)

python

This produces the following output (a lovely report).

As a Business Intelligence Analyst, I have conducted a precise competitive analysis of the top three frontend deployment alternatives to Vercel: **Netlify** , **Cloudflare Pages** , and **Google Cloud Run**.

All findings have been structured using `pandas` and exported to `/` (the current working directory) as:
1. `competitive_matrix.csv` — The raw, structured dataset.
2. `competitive_analysis.md` — A comprehensive, reader-ready report including a detailed markdown comparison matrix, architectural breakdowns, limitation analyses, and a tailored recommendation framework.

All data has been verified against official vendor pricing, product, and developer documentation as of **June 9, 2026**. All currency values are normalized in **USD**.

---

### Core Finding Highlights

#### 1. Netlify
* **The Architectural Shift (April 2026):** Netlify made a massive strategic update to its Pro plans, moving from a seat-based model ($19/member/month) to a **flat $20/month per organization** [10]. This includes unlimited team members (Owners, Developers, Reviewers, and Git Contributors) [10], which is highly disruptive compared to Vercel's strict per-seat billing.
* **The Credits Trap:** Usage is now managed entirely via a unified credit-based model (300 credits/mo free, 3,000 on Pro) [2, 10]. However, credits are consumed fast: bandwidth costs 20 credits per GB [2, 10] (meaning Free tier is only **~15 GB max** and Pro is only **~150 GB max** if solely used for traffic). If Free tier credits run out, **all site traffic pauses immediately** (no auto-recharge is supported on Free) [2, 11]. 
* **Capabilities:** Highly integrated features like Netlify Database (managed Postgres via Neon) [4], Blob storage, Forms, and Auth [10]. Serverless timeout is 10s on Free/Personal [2] and 26s on Pro [2].

#### 2. Cloudflare Pages
* **Unmetered Freedom:** Genuinely **unlimited and unmetered static bandwidth and requests** across all tiers (including the $0 Free tier) [24, 25, 27].
* **The Pro Tier ($20/mo billed annually / $25/mo monthly):** Tied directly to Cloudflare's Workers Paid plan [25, 27]. It increases build limits from 500/mo to 5,000/mo, concurrent builds from 1 to 5, and the file-count ceiling per project from 20,000 to 100,000 assets [31] (unlocked via the `PAGES_WRANGLER_MAJOR_VERSION=4` env variable) [31].
* **Edge Isolates Constraints:** While running serverless code on Cloudflare's global network of 310+ cities is blazingly fast with zero cold starts [24, 33], it uses a **strict V8 edge runtime** [24]. Standard Node.js library modules (`fs`, `path`, native `crypto`) do not run natively [24], forcing developers to compile meta-frameworks like Next.js via edge adapters (e.g., `@cloudflare/next-on-pages` or OpenNext) [24] which restricts certain features like Incremental Static Regeneration (ISR).

#### 3. Google Cloud Run
* **Pure Container Portability:** Cloud Run runs any application, language, or compiled binary (Node.js, Python, Go, Rust) packaged in a standard Docker container [37, 39]. It runs full Node.js natively [39], ensuring 100% Next.js feature parity (ISR, Server Actions, dynamic image optimization) with zero edge-runtime workarounds [39].
* **No Monthly Base Fee:** Operates on a pure pay-as-you-go serverless model (billed in granular vCPU-seconds and GiB-seconds) [41], backed by a generous Always Free tier (2 million requests/mo, 180,000 vCPU-seconds, 360,000 GiB-seconds, and 120 daily Cloud Build minutes free) [37, 38, 41]. 
* **The Infrastructure Overhead:** Not a standard "push-to-deploy" platform. Developers must write Dockerfiles, configure Artifact Registry, and manage IAM and networking [37, 39]. It is regionally hosted; to get a global CDN with SSL mapping, you must set up Cloud CDN and a Global HTTP Load Balancer [37] (~$20-$30/mo base fee) and navigate container cold starts (2 to 10+ seconds) [37] and expensive internet egress rates ($0.085 - $0.12 per GB) [37].

---

### Structure of Generated Files

#### 1. `competitive_matrix.csv`
A raw, tabular CSV structured for business intelligence pipelines, featuring the following schema:
- `Platform Name`
- `Free Tier Pricing (USD)`
- `Free Tier Bandwidth Limit`
- `Free Tier Build Limit`
- `Free Tier Sites/Projects Limit`
- `Free Tier Key Specs & Features`
- `Paid/Pro Tier Price (USD)`
- `Paid/Pro Tier Features Unlocked`
- `Key Differentiating Features`
- `Notable Limitations & Developer Complaints`
- `Date of Research`
- `Source URLs`

#### 2. `competitive_analysis.md`
A professionally formatted report including:
* **Executive Summary:** Contextualizing why frontend teams are exploring alternatives to Vercel in 2026.
* **Structured Comparison Table:** Transposed for high-density reading and side-by-side comparison.
* **Deep-Dive Section:** Dedicated analyses of the Free limits, paid features, unique differentiators, and community complaints for Netlify, Cloudflare Pages, and Google Cloud Run.
* **Architectural Recommendation Flowchart & Matrix:** Tailored decision pathways based on project profile:
  * *Static / JAMstack / Zero-Budget* $\rightarrow$ **Cloudflare Pages**
  * *Collaborative Teams / Rapid Prototyping / Seat-Free DX* $\rightarrow$ **Netlify**
  * *Complex Server-Side Rendering / Backend Pipelines / Custom Docker* $\rightarrow$ **Google Cloud Run**

---

### Source Verification & Citations

1. **Netlify:**
   - [Official Pricing & Plans](https://www.netlify.com/pricing/)
   - [Introducing Seat-Free Collaborative Billing (April 14, 2026)](https://www.netlify.com/blog/pricing-netlify-for-3-billion-builders/)
   - [Credit-Based Pricing Documentation](https://docs.netlify.com/manage/accounts-and-billing/billing/billing-for-credit-based-plans/credit-based-pricing-plans/)
   - [Netlify Free Tier Credit Analysis (Temps)](https://temps.sh/compare/vs-netlify)

2. **Cloudflare Pages:**
   - [Workers & Pages Pricing Matrix](https://www.cloudflare.com/plans/developer-platform/)
   - [Official Pages Limits Documentation](https://developers.cloudflare.com/pages/platform/limits/)
   - [Cloudflare Pages Platform Features](https://pages.cloudflare.com/)
   - [Cloudflare Pages Edge Limitations (Temps)](https://temps.sh/compare/vs-cloudflare-pages)

3. **Google Cloud Run:**
   - [Official Cloud Run Pricing Breakdown](https://cloud.google.com/run/pricing)
   - [Google Cloud Free Tier Inclusions](https://cloud.google.com/free)
   - [Cloud Run Quotas & Limits](https://docs.cloud.google.com/run/quotas)
   - [Cloud Run Cost Optimization & Egress Guide (Cloudchipr)](https://cloudchipr.com/blog/cloud-run-pricing)

The generated files are saved directly in your working directory and are immediately available for download or integration into your reporting pipelines. Let me know if you would like me to modify the analysis parameters or explore a specific platform further!

plaintext

Building on the Analysis (Multi-Turn)

You can do a follow up too, by using the previous environment and interaction to take the competitive_matrix.csv generated and creating some visualization out of it. While the code below retrieves only the text output, you can use the technique shown below to download the environment sandbox and extract out the files generated.

# Follow-up: generate a visual chart from the data we just collected
interaction_2 = client.interactions.create(
    agent="antigravity-preview-05-2026",
    environment=interaction.environment_id,
    previous_interaction_id=interaction.id,
    input="""
    Using the competitive_matrix.csv you just created:
    1. Create a grouped bar chart comparing the free tier limits across all 3 platforms
    2. Create a pricing comparison chart for the paid tiers
    3. Save both charts as PNG files with clear labels and a professional color scheme
    4. Add the charts as embedded images in the competitive_analysis.md report
    """
)
print(interaction_2.output_text)

python

Key Concepts Introduced: Web browsing + code execution in the same task. The agent searches the live internet, then writes Python code to structure and visualize the data — all in one flow.

More Use Cases

I plan to keep adding to this document with more use cases, as this solution matures with more features. Stay tuned for updates.

Best Practices

Here are the architectural patterns that will serve you well in production:

Build to Delete

Model performance improves rapidly. Design your agents with the expectation that they’ll be rebuilt with newer models soon. Keep configurations modular — AGENTS.md + SKILL.md files are easy to swap. Don't over-engineer the orchestration layer.

Treat Agents as Microservices

Don’t build one massive agent with a 2,000-word system prompt. Decompose complex problems into specialized sub-agents:

Errors as Inputs, Not Crashes

In robust agentic architectures, errors are data and are inputs for the agent to self-reflect and correct. The agent reads a TypeError, reasons about the cause, and fixes it. Don't wrap everything in try/except blocks that swallow errors. Let the agent see them.

Evals Over Unit Tests

Agent behavior is non-deterministic. Testing focuses on evaluation metrics rather than exact output matching:


# ❌ Don't: Assert exact output
assert agent_output == "The answer is 42"

# ✅ Do: Evaluate behavioral success rate
results = [run_agent(task) for _ in range(20)]
success_rate = sum(1 for r in results if r.meets_criteria) / len(results)
assert success_rate >= 0.85 # Agent succeeds at least 85% of the time

Token Cost Awareness

Because Antigravity operates an autonomous reasoning loop, a single prompt can trigger many internal operations. Expect something around this ball park:

Implement strict timeouts and monitor trace lengths during development. Use system_instruction to tell the agent to be concise when you don't need verbose reasoning.

Error Handling Patterns

Resources

Official Documentation: ai.google.dev/gemini-api/docs/custom-agents
Gemini Managed Agents: Developer Guide : https://www.philschmid.de/gemini-managed-agents-developer-guide
Video: Managed Agents Deep Dive: youtube.com/watch?v=Psa8mLikdag
Video: Getting Started Tutorial: youtube.com/watch?v=0YXe7u-i1qU
Google AI Studio: aistudio.google.com

Ideas for Your Next Agent

CI/CD Pipeline Agent — monitors your GitHub repo, runs tests on every push, opens fix PRs for failures
Documentation Generator — reads your codebase and generates comprehensive API docs
Data Pipeline Orchestrator — connects to your warehouse, runs transformations, validates output
Customer Support Triage Agent — reads tickets, categorizes severity, drafts responses, escalates critical issues
Research Assistant — takes a topic, searches papers and articles, writes a literature review with citations

Final Thought

Managed Agents represent a fundamental shift in how we build with AI. You’re no longer building the infrastructure around the AI, you’re simply giving the AI a goal and a sandbox, and letting it work. The sandbox is the abstraction. The agentic loop is the engine. And the Interactions API is your single point of contact with all of it.

Most importantly, start small and set limits on what the agent can do autonomously. Then scale up.

Happy building.

Google Cloud Platform Technology Nuggets — May 16–31, 2026

Romin Irani — Wed, 03 Jun 2026 06:19:11 +0000

Welcome to the May 16–31, 2026 edition of Google Cloud Platform Technology Nuggets. The nuggets are also available on YouTube.

Infographic for the post generated by NotebookLM

AI and Machine Learning

If you are looking to stay updated on the latest Google Cloud AI tools, you should bookmark this link that covers updates made across the months.

There has been a spate of announcements at Google Cloud Next 2026 in April and Google I/O held in May introduced several other releases too, that included:

Gemini 3.5 Flash models
Gemini Omni (any output from any input, starting with video)
Google Antigravity in its new version
Managed Agents on Agent Platform

Check out the post that highlights these announcements in detail.

Google Cloud has introduced the general availability of Nano Banana 2 (Gemini 3.1 Flash Image) and Nano Banana Pro (Gemini 3 Pro Image) on the Gemini Enterprise Agent Platform and the Gemini API. These enterprise-grade models allow developers to integrate image generation and editing capabilities directly into their applications and workflows.

Long-running agent workflows is where the industry is moving. But how to manage and operate them reliably and efficiently. Google believes you can use Agent Executor, an open-source runtime standard designed for executing, resuming, and deploying distributed AI agents. The key technical capabilities of this standard include:

Durable execution to automatically resume progress via event logs and snapshotting after human-in-the-loop steps or outages
Secure isolation through sandboxes to safely execute code and manage multi-tenant workloads
Session consistency using a single-writer architecture to prevent state corruption
Connection recovery to allow disconnected clients to reconnect and backfill missed responses
Trajectory branching to let agents test alternative decision paths using checkpoints.

Check out the blog post for more details.

Looking to deploy and optimize large language models on mobile devices, take a look at new benchmarking and debugging capabilities within the Google AI Edge Portal. The platform allows developers to run automated testing across a fleet of over 120 Android device types to evaluate performance across CPU and GPU backends using the LiteRT-LM format. Check out the blog post.

Data Analytics

Data Agent Kit is an open-source collection of data engineering and data science skills, Model Context Protocol (MCP) tools, and plugins designed to connect development environments like VS Code and various CLIs with enterprise data. The kit provides pre-codified skills for tasks like query optimization, data validation, and troubleshooting, alongside MCP tools that create secure connections to platforms like BigQuery, AlloyDB, and Google Cloud Storage without requiring manual pipeline code. Check it out.

Remote Model Context Protocol (MCP) Server for AlloyDB is now in General Availability. The Remote MCP Server for AlloyDB runs on fully-managed Google Cloud infrastructure and exposes an HTTP endpoint that connects your AI applications to your data. It is integrated with the Agent Registry, supports fine-grained authorization, allows agents to not just run queries but also manage instances and more. Check out the blog post that highlights the features and a demo of how an agent has been integrate to work with AlloyDB.

Connected Sheets, which provides a direct connection between Google Sheets and BigQuery, has been there for a while. Instead of exporting data as CSVs, which causes version control and security risks, this feature allows users to perform ad-hoc analysis, modeling, and reporting on live data without writing SQL. Check out a blog post, which gives you a quick overview of Connected Sheets, walk through real-world use cases, and show you how to perform enterprise-grade data analysis using BigQuery directly in Google Sheets.

Databases

AlloyDB has got a significant upgrade to its High Availability (HA) architecture: Hot Standby. With the new architecture, the standby node continuously streams and applies write-ahead logs (WAL) from the primary node. This change allows the system to detect failures and promote the standby node within 30 seconds, dropping the average failover time to approximately 15 seconds. Furthermore, because the standby node constantly replays logs, its memory caches stay warm, allowing the database to maintain its transaction-per-second rate immediately after a failover without any performance brownouts. This feature is automatically rolled out to new instances on PostgreSQL 18 at no additional cost, with earlier versions receiving support in the following months. For more details, check out the blog post.

Developers & Practitioners

You are a developer working on building out Agents on Google technologies. How do you know which one to pick to develop these agents, since there are quite a few ranging from no-code to heavily code-driven frameworks. The article is an excellent way to step back and look at the existing landscape today to develop agents on Google Cloud, with options ranging from low code (Agent Studio) to ADK 2.0. Included in the spectrum is the recently announced Managed Agents API, which allows you to define agentic behavior and let Google Cloud handle the heavy lifting, acting as an agent-as-a-service with nothing to manage.

It is given that we need to secure our credentials, especially API Keys that may have been configured to have access to several Google Cloud services and could be a problem, if misused. But what are the recommended best practices to manage and secure your API Keys. This post goes into the detail while highlighting services like Secret Manager to manage/rotate keys, regular audits and more.

Reducing friction for developers trying out developer tools from Google and eventually deploying them on Google, has traditionally faced the common struggle of folks signing up for billing first. With a newly announced deeper integration between Google AI Studio and Google Cloud, you can now vibe code with Google AI Studio with a possible persistent layer backed by Firestore and deploy two applications on Google Cloud Run, without the need of a credit card. Check this out.

Gemini Live Agent Challenge has announced the winners and key highlights from the contest that asked developers to integrate real-time multimodal capabilities using the Gemini Live API, the Agent Development Kit (ADK), and Google Cloud infrastructure. The global challenge resulted in projects across three main categories:

Live Agent (Voice)
Creative Storyteller (Audio / Visual)
UI Navigator (Gesture-driven interactions)

Notable winners included ORION, a voice-directed surgical co-pilot for robotic surgery; drone-copilot, which replaces manual joysticks with natural language voice commands for navigation and autonomous visual inspections; and Moonwalk, a hands-free desktop assistant that automates workflows by controlling the keyboard and mouse through voice.

AI agent conversations usually go back and forth with a series of questions and usually the interactions end up with just text data and interpreting the intent and extracting data can be not just challenging but more efficient in terms of number of interactions. What if a set of questions that the Agent wants to ask of the user, is converted into a simple UI with the right kind of input controls to select the data from. For e.g. a dropdown, a few checkboxes, etc. Enter A2UI (Agent to UI) Protocol, an open protocol for agent-driven user interfaces and a great example of how this protocol can be embedded into the front-door Gemini Enterprise application is demonstrated in this blog post.

Customers

One of the interesting blog posts that I look forward to each month is one in which we can learn what customers have been building with Google Cloud. For the month of May, there were interesting things that they built. Some of which include:

Glance automated its short-form video extraction pipeline by combining Google Cloud Speech-to-Text v2, Gemini 2.5 Flash, the Google Vision API, Samurai object tracking, OpenCV, and MoviePy.
Urban Outfitters migrated its 11TB Oracle database to AlloyDB for PostgreSQL to power its IBM Sterling OMS, deploying two read replicas to lower data latency for reporting and analytics.
Movix engineered an agentic AI solution for dental lab quality control using the Gemini Enterprise Agent Platform alongside Cloud Run with L4 GPUs and Compute Engine VMs.

Check out the post for more of what cool things that customers built.

Containers and Kubernetes

Google Kubernetes Engine (GKE) Agent Sandbox helps you manage isolated, stateful, and single-replica workloads on GKE. It is optimized for use cases like AI agent runtimes, where untrusted, LLM-generated code must be executed in a secure and performant environment. The GKE Agent Sandbox is now generally available and there is a new introduction too, Agent Substrate. This open source project introduces a minimal control plane that moves agents on and off ready compute capacity in real-time while integrating data locality directly into its scheduler to minimize overhead. . Check out the blog post.

Security and Identity

If you are looking to protect your systems from high-speed, automated cybersecurity threats, Google Cloud has introduced Google AI Threat Defense, an autonomous platform built on a four-step framework: Prepare, Scan and Prioritize, Remediate, and Monitor. The system reduces attack surface exposure through Wiz, which maps your live environment and uses an AI penetration testing agent to validate exploitable pathways. When vulnerabilities are discovered, the platform incorporates Mandiant expertise for response planning while CodeMender automatically generates fixes, analyzes library dependencies, and creates verification tests directly inside the developer’s integrated development environment or command-line interface. Check out the blog post for more details.

The second Cloud CISO Perspectives for May 2026 is out. If you are looking to build an AI-ready security program for the public sector, this article outlines a structured, 12-month roadmap designed to manage complex systems and reduce operational toil. The plan is organized across five core workload domains: executive alignment, process optimization, talent augmentation, posture elevation, and advanced governance.

Infrastructure and Networking

There have been several architectural updates to Google’s global and data center networks designed to handle the specific traffic patterns and scale required for AI training and inference workloads. The new Virgo Network serves as a flat, two-layer scale-out data center fabric that connects up to 134,000 eighth-generation TPU chips, delivering increased bandwidth, lower latency, and autonomous reliability features like automated hang and straggler detection to isolate faulty instances. Read more here.

Given the kind of infrastructure that Google runs, it should be interesting to learn about how they ensure that any optimizations that they introduce to their infrastrcture takes place safely. In fact they run a fleet-wide, machine-level A/B experimentation framework. Instead of testing at the application level, Google enables changes on individual machines across a balanced 1% subset of the fleet to capture system-wide effects for core components like libraries, compilers, kernels, and cluster management systems. Check out the details here.

DevOps and SRE

SRE AI is an initiative that integrates agentic AI into Site Reliability Engineering. This includes deploying autonomous AI agents across the entire software development lifecycle. These agents assist in reliability design by creating and updating playbooks, use models like TimesFM for anomaly detection and alert enrichment, and orchestrate incident management by summarizing communications and drafting postmortems. For more details, check out the blog post.

Application Development

Google Cloud has introduced App-centric maintenance visibility within Unified Maintenance to shift planned maintenance tracking from an infrastructure-focused view to a business-oriented view. By integrating directly with App Hub, Unified Maintenance automatically aggregates the maintenance schedules of registered resources (GKE clusters, GCE VMs, or AlloyDB instances) into a single dashboard centered around the application as the primary unit of management. To use this feature, teams need to enable the Maintenance API and configure application boundaries in the Google Cloud Console. For more details, check out the blog post.

Continuing on Application Development, we now have a public preview of AppLifecycle Manager Feature Flags (ALM FF). This service decouples feature releases from code deployments, allowing teams to ship code with new features disabled by default and use a toggle as an instant kill switch if issues arise. Built on the open-source OpenFeature standard and the flagd evaluation engine, ALM FF uses Common Expression Language (CEL) to enable targeted rollouts, such as percentage-based traffic ramping or precise allowlisting for specific internal teams and testers. Check out the blog post.

Learn about Google Cloud

If you have been working with traditional transactional databases and are looking to transition enterprise data from static reports to autonomous systems, Google Cloud outlines a structural evolution across five technical scenarios to manage security, costs, and accuracy. These five scenarios are:

Scenario 1: The Static API Contract, which uses pre-written, parameterized SQL queries for deterministic performance.
Scenario 2: Custom Agent with SQL Generation, where an LLM translates natural language into queries using schema metadata.
Scenario 3: Conversational Analytics, which uses a platform-native engine grounded in verified query libraries to enforce business logic.
Scenario 4: Managed MCP Tools introduces the open-source Model Context Protocol (MCP) to decouple the reasoning layer from tool execution via a managed BigQuery server. This helps to scale across different systems.
Scenario 5: Custom Hosted MCP Servers gives engineers full control to build specialized, multi-source tools on infrastructure like Cloud Run, allowing for programmatic governance and custom data abstraction.

Check out the blog post that provides detailed guidance, queries and more.

Write for Google Cloud Medium publication

If you would like to share your Google Cloud expertise with your fellow practitioners, consider becoming an author for Google Cloud Medium publication. Reach out to me via comments and/or fill out thisform and I’ll be happy to add you as a writer.

Stay in Touch

Have questions, comments, or other feedback on this newsletter? Please send Feedback.

If any of your peers are interested in receiving this newsletter, send them theSubscribe link.

Antigravity CLI Tutorial Series: Part 2 : Conversations, Conversations and Conversations

Romin Irani — Sun, 24 May 2026 13:15:36 +0000

Welcome to Antigravity CLI Tutorial.

The Series:

Part 1 : Getting Started

Part 2 : Conversations, Conversations, Conversations (this blog)

Codelab : If you prefer to do a hands-on, step-by-step instructional codelab, go directly to the “Getting Started with Antigravity CLI Codelab”.

In this part of the series, we are going to understanding the mechanics of Conversations in Antigravity CLI.

You might already have your own definition of what a conversation means? And you would be right in your approximate definition of it. It is definitely a sequence or a thread of messages exchanged between you (user) and the agent.

But you would have multiple questions pop up like:

Are these conversations stored somewhere?
How do we manage multiple threads of conversation? Each thread having its own sequence of unique user and agent interactions.
Can we switch from one conversation to another?

And definitely a lot more questions along similar lines. What follows is my understanding of what Conversations are in Antigravity CLI and an attempt to get the answers to the above questions.

I call these as my experiments since the documentation is sparse at the time of writing and the source code is not open for me to take a peek into. So please correct me if I have hallucinated unintentionally. :-)

What is a Conversation?

First up, let usattempt to define what a conversation means and what better than to ask Antigravity CLI itself. It came up quite well:

In the context of Antigravity CLI, a conversation is an isolated work session or execution thread identified by a unique Conversation ID (e.g., 3b4a1d20–3968–4ed2–90b3–00eea3060b02 ).

Here is what defines a conversation:

State and History: Every conversation preserves a history of interactions (user requests, agent responses, tool calls, and system messages) serialized as JSON Lines (JSONL) transcripts under

/brain//.system_generated/logs/ .
Dedicated Artifacts: Each conversation has its own storage directory

( /brain// ) where structured markdown documents like the implementation_plan.md , task.md , and walkthrough.md are saved and updated.
Scratch Space: Conversations have a dedicated scratchpad directory ( /brain//scratch/ ) for temporary test scripts, helper files, or data files that persist across steps.
Agent Tree: When a main agent invokes a subagent, a new child conversation is spawned with its own ID, allowing agents to work in parallel on specialized sub-tasks while maintaining isolated context.

What is an appDataDir?

Good question. On my mac, it is in my $HOME/.gemini/antigravity-cli folder or ~/.gemini/antigravity-cli folder. So inside of this directory, you will find the following:

Inside this directory, you will find the following folder and sub-folders under it (not all subfolders are described):

brain/ : Contains subdirectories for each conversation (using their Conversation ID) containing:

— .system_generated/logs/ : Chat transcripts ( transcript.jsonl , transcript_full.jsonl ).

— Artifacts: Markdown files like implementation_plan.md , task.md , and walkthrough.md .

Conversation Management commands

There are several in-built commands in Antigravity CLI that we can use for conversation management. They are:

• /clear : Clears the screen and starts a fresh conversation thread.

• /resume (or /switch ): Displays a menu showing your previous conversations, allowing you to choose one to resume.

• /rewind (or /undo ): Rolls back the active conversation history to a previous step (useful if a command failed or you want to try a different direction).

• /fork : Branches the current conversation into a new workspace from a specific step, preserving history up to that point.

/rename : Renames the active conversation with a custom, readable title.

Let’s see it work

Let’s ensure that we are starting a fresh conversation thread. To do that, you can use /clear command. This can be used anytime to create a new conversation. This does not lose any of the previous conversation and we can always switch back to previous conversation threads. We will see all of that in a while.

But for now, just ensure that you have used the /clear command and are ready in Antigravity CLI.

Give the following prompt:

What is Google Cloud Run?

Antigravity CLI gets down to work and produces the following output:

● WebSearch(Google Cloud Run overview features) (ctrl+o to expand)

  Google Cloud Run is a fully managed, serverless platform by Google Cloud that allows you to run containerized applications and services without having to manage the underlying server infrastructure. It combines the flexibility of        
  containers with the simplicity of serverless computing.                                                                                                                                                                                      

  ### Key Features                                                                                                                                                                                                                             

  • Fully Managed & Serverless: Google automatically handles infrastructure management, including server provisioning, operating system maintenance, and scaling.                                                                              
  • Automatic Scaling: Cloud Run scales automatically based on incoming request traffic. It can scale up to thousands of instances to handle high demand, and scale down to zero when there is no traffic, meaning you only pay when your      
  application is actively handling requests.                                                                                                                                                                                                   
  • Any Language or Library: Since it runs Docker/OCI-compliant containers, you can write your application in any programming language (e.g., Python, Node.js, Go, Java, Rust) and use any system library or custom dependency.                
  • Deploy from Source or Container: You can deploy an existing container image from Google Artifact Registry or deploy directly from your source code repository. If deploying from source, Cloud Run uses Google Cloud Buildpacks to         
  automatically package your code into a container.                                                                                                                                                                                            
  • Two Execution Modes:                                                                                                                                                                                                                       
      • Cloud Run Services: For web apps, APIs, microservices, or event-driven applications that respond to incoming web/HTTP requests or gRPC calls.                                                                                          
      • Cloud Run Jobs: For short-lived, run-to-completion tasks (like database migrations, nightly backups, or batch data processing) that do not serve web traffic.                                                                          
  • Hardware and AI Acceleration: It supports deploying workloads on GPUs (such as NVIDIA L4) and using larger machine configurations, making it a viable serverless platform for hosting Large Language Models (LLMs) and running AI inference
  workloads.                                                                                                                                                                                                                                   
  • Integrations: It integrates natively with other Google Cloud services (such as Pub/Sub, Cloud Storage, and Eventarc for event-driven workflows) and supports VPC connectivity to securely access private databases or other internal       
  resources.

But what has it done behind the scenes to persist this conversation thread.

Step 1

The Antigravity CLI instantly performs the following directory setup (I am assuming the following conversation id → 11111111–2222–3333–4444–555555555555):

Creates the Conversation Root Folder:

~/.gemini/antigravity-cli/brain/11111111–2222–3333–4444–555555555555/

Creates the System Logs Folder:

~/.gemini/antigravity-cli/brain/11111111–2222–3333–4444–555555555555/.system_generated/logs/

Creates the Scratchpad Directory:

~/.gemini/antigravity-cli/brain/11111111–2222–3333–4444–555555555555/scratch/ (This folder remains empty until the agent needs to write temporary test scripts or run one-off diagnostics).

Step 2: Logging the Initial Prompt (Internal System Logs)

The CLI creates two JSON Lines files under the .system_generated/logs/ folder:

• transcript.jsonl (assuming that this is a token-efficient log containing truncated text for large outputs)

• transcript_full.jsonl (assuming that this is a full, untruncated log containing exact tool results and text)

If you visit the transcript.jsonl file, you will notice that a JSON record representing your first input step is appended (few fields only since there is a lot of metadata too):

{
 "step_index":0,
 "source":"USER_EXPLICIT",
 "type":"USER_INPUT",
 "status":"DONE",
 "content":"What is Google Cloud Run?"
}

You will also see multiple steps being recorded next in terms of how Antigravity CLI is planning out its execution. I will only reproduce the steps / types, etc and it will be good enough for you to understand. I encourage you to inspect the files on your machine to see all the wonderful details.

{"step_index":1,"source":"SYSTEM","type":"CONVERSATION_HISTORY"...}
{"step_index":2,"source":"MODEL","type":"PLANNER_RESPONSE","status":"DONE","created_at":"2026-05-24T12:14:37Z","tool_calls":[{"name":"search_web","args":{"query":"\"Google Cloud Run overview features\"","toolAction":"\"Searching the web\"","toolSummary":"\"Web search\""}}]}
{"step_index":3,"source":"MODEL","type":"SEARCH_WEB","status":"DONE","created_at":"2026-05-24T12:14:38Z","content":"Created At: 2026-05-24T12:14:38Z\nCompleted At: 2026-05-24T12:14:43Z\nThe search for \"Google Cloud Run overview features\" returned the following summary:\nGoogle Cloud Run is a fully managed, serverless platform that allows you to run containerized applications and services without managing the underlying infrastructure[1][2][3]. It is designed to combine the flexibility of containers with the simplicity of a serverless environment[4].\n\n### Core Features\n\n* **Fully Managed & Serverless:** Google handles all infrastructure management, including provisioning, scaling, and maintenance[1][2]. You simply provide your code or container[3][4].\n* **Automatic Scaling:** Cloud Run s.....}
...
{"step_index":5,"source":"MODEL","type":"PLANNER_RESPONSE","status":"DONE","created_at":"2026-05-24T12:14:46Z","content":" **Google Cloud Run** is a fully managed, serverless platform by Google Cloud ...}

In this way, your current conversation as you go back and forth is persisted.

See what happens if you give a follow up message that says:

What kind of applications can I deploy on Google Cloud Run?

Once you get the response in Antigravity CLI terminal, go back to the conversation id folder and you will see additional steps in the transcript.jsonl file:

{"step_index":6,"source":"USER_EXPLICIT","type":"USER_INPUT","status":"DONE","created_at":"2026-05-24T12:27:18Z","content":"<USER_REQUEST>\nWhat kind of applications can I deploy on Google Cloud Run?\n</USER_REQUEST>\n<ADDITIONAL_METADATA>\nThe current local time is: 2026-05-24T17:57:18+05:30.\n</ADDITIONAL_METADATA>"}
{"step_index":7,"source":"MODEL","type":"PLANNER_RESPONSE","status":"DONE","created_at":"2026-05-24T12:27:18Z","content":"You can deploy a wide variety of applications on...}

Step 3: Agent Analysis and Planning (If coding changes are needed)

Now, let’s say we go a step further and ask it to actually generate/code a sample application for us that can be deployed on Cloud Run:

Create a single page HTML / JavaScript application to deploy on Cloud Run that takes my name and returns me a greeting.
Let's plan it out first.

Here I am specifically asking it to plan it out first. It comes back saying:

 I have created the implementation plan for the Google Cloud Run greeting application.                                                                                                                                                        

  Please review the proposed design and files in the implementation_plan.md artifact. Once you approve, let me know and we will proceed to verify it.

This behind the scenes creates:

~/.gemini/antigravity-cli/brain/11111111–2222–3333–4444–555555555555/implementation_plan.md

Depending on how you proceed, additional markdown files (walkthrough, task list, etc) will be created in the same folder.

As an experiment, go ahead with approving the implementation plan. This will make Antigravity CLI generate the code, test out the server, etc. This will result in additional folders being created but all within the brain/CONVERSATION_ID folder.

If you navigate to your app data folder during/after a coding conversation, here is exactly what you would start seeing something like this:

~/.gemini/antigravity-cli/
└── brain/
└── 11111111–2222–3333–4444–555555555555/ ← Root of the conversation
├── .system_generated/
│ └── logs/
│ ├── transcript.jsonl ← Truncated log
│ └── transcript_full.jsonl ← Untruncated full log
├── implementation_plan.md ← Technical design spec
├── task.md ← Interactive checklist
└── walkthrough.md ← Work summary & verification

A few other things worth mentioning are:

You will find a history.jsonl within the ~/.gemini/antigravity-cli folder that seems to be a index of all conversations.
A conversations folder that holds the conversations in a protocol buffer format. We can leave it as is for now.

Let’s Rewind

What if we want to go back at a point in time in the conversation. Remember we started with asking about Google Cloud Run, then we asked it to generate code for the application and so on. As a result of which, several code files, artifacts etc have been generated.

If I go into shell mode and see the current files in the folder, you can see from the output below, the files that are currently present. So far so good.

● ! ls
  ⎿ Dockerfile
     node_modules
     package-lock.json
     package.json
     public
     README.md
     server.js

Now, give the /rewind command and you should see a list of all interactions that you have had. In my case, you see the current conversation thread with the list of interactions. I can use the keyboard to go up at the specific point in time before the files were generated (8 files changed, etc).

──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
Rewind Conversation

  What is Google Cloud Run?

> What kind of applications can I deploy on Google Cloud Run?

  Create a single page HTML / JavaScript application to deploy on Cloud Run tha...
    8 files changed +583 -1

  Could you first plan it out?
    1 artifact generated

  what is the history.jsonl file that you are managing for the conversations

  what is a .pb file and how are you using it for conversations

  (current)

Keyboard: ↑/↓ Navigate enter Select esc Cancel

Once I select to rewind it to a step before all the files were generated and execute that step, it will remove the files generated as is evident from the outputs that I now see.

● ! ls
  ⎿ node_modules
     package-lock.json
     public

The implementation_plan.md and other artifact files also go away from the brain/CONVERSATION_ID folder that we earlier saw. You can try out these scenarios on your machine.

Saving a Conversation with a different name

At any point in time, you can save the conversation with a name that is easier or makes sense to you in terms of the entire thread. Just use the /rename command.

In Antigravity CLI, I simply give the rename Google Cloud Run basics to rename this conversation. It comes back with the following message:

> /rename
  ⎿ Conversation renamed to: Google Cloud Run basics

Switching between Conversations

You can use the /resume or /switch command to switch to another conversation. For example, I see the following:

   CLI Antigravity (tab to cycle)

  Conversations
  Type to search...
> [CURRENT] Google Cloud Run basics 10 steps 8m ago
  Understanding Antigravity CLI Conversations 24 steps 52m ago
  hello 4 steps 1h ago

Keyboard: ↑/↓ Navigate ←/→ Page enter Select f2 Rename ctrl+delete Delete tab Switch Tab esc Go back / Clear search

You can see that our current context is now with our preferred name Google Cloud Run basics and the other ones that you see in the list are the ones that I had here. But you might see another list.

Select any one of these to switch to that conversation and carry on that conversation from there or maybe even rewind, etc.

Switching to an Antigravity conversation

If you have been paying attention to the output shown in the /switch command, you might see an Antigravity and CLI option. This might happen only if you have also installed the non-CLI option i.e. Antigravity on your machine. In my case I have and have interacted a bit with it.

But what is pleasantly surprising is that it is now showing me conversations that have been saved via Antigravity and allowing me to import them. Whew! Let’s try this out:

   CLI Antigravity (tab to cycle)

  Conversations
  Type to search...
> Extracting Invoice Information [Import this conversation? (y/n)] 20 steps 2h ago
  Generate a events website but let's discuss the requirements first. 67 steps 1d ago

Keyboard: ↑/↓ Navigate enter Select tab Switch Tab esc Go back / Clear search

So I select one of the conversations (Extracting Invoice Information) and then press on Enter. It asks me that it needs to import this conversation. This brought up the previous conversation and I was able to carry on with a new message in the thread. Wonderful. Probably this needs a lot more testing.

  <PREVIOUS _ CONVERSATION _ THREAD >

────────────────────────────────────────────────────────────
> What are the files sizes for each of the invoices

● ListDir(/Users/romin/agy-cli-projects/invoice-processing) (ctrl+o to expand)

  Here are the file sizes for each of the invoice image files in your directory:                                                                                                                                                               

  • inv1.png: 273,828 bytes (approx. 273.8 KB)                                                                                                                                                                                           
  • inv2.png: 369,086 bytes (approx. 369.1 KB)                                                                                                                                                                                           
  • inv3.png: 446,932 bytes (approx. 446.9 KB)                                                                                                                                                                                           
  • inv4.png: 343,328 bytes (approx. 343.3 KB)                                                                                                                                                                                           

  (Note: The CHUBB.pdf insurance document size is 42,965 bytes / approx. 43 KB).

One more thing

If you quit your Antigravity CLI at this point, you will notice that there is a message at the end that looks something like this:

Resume: agy --conversation=d1d8a55b-cc27-4dd4-bc62-2f73015960d2 (or -c)

That’s right. Antigravity CLI comes with a command line option to resume a specific conversation via the --conversation or -c parameter. This value has to be the unique conversation id that you see. I think this is useful but might be a bit unwieldy to remember or use.

In any case, the key message is that you now what is going on with this unique conversation id , where the stuff is persisted on your local machine and can discover more. In any case, you can always launch Antigravity CLI and use the /switch command to go to a specific conversation thread. Just remember to use /rename to name them in a way that you understand.

Conclusion

While a conversation in Antigravity CLI is something that is managed behind the scenes for you, it is helpful to understand how the tool is working. Hopefully these examples give you a good idea of what is happening under the hood. I will keep adding more examples to this as I understand this better. See you in latter parts of the series.

Antigravity CLI Tutorial Series

Romin Irani — Fri, 22 May 2026 15:08:49 +0000

Getting Started with Antigravity CLI : Tutorial Series

Welcome to the Antigravity CLI Tutorial Series. Antigravity CLI is the terminal-first interface to work with Antigravity Agents. It can be used for all kinds of tasks ranging from coding to automating repeated tasks.

Welcome to Antigravity CLI Tutorial.

The Series:

Part 1 : Getting Started(this blog)

Part 2 : Conversations, Conversations, Conversations

Codelab : If you prefer to do a hands-on, step-by-step instructional codelab, go directly to the “Getting Started with Antigravity CLI Codelab”.

Antigravity CLI is part of the Antigravity 2 release. As the documentation states, “It brings the same core agentic capabilities as Antigravity 2.0 — including multi-step reasoning, multi-file editing, tool calling, and conversation history — directly to your terminal.”

Reference: https://antigravity.google/product/antigravity-cli

Here are a few highlights at the time of the initial announcement, in terms of what Antigravity CLI brings to the table:

Faster Execution: The new CLI is built in Go, making it noticeably snappier and more responsive than its predecessor.
Asynchronous Workflows: This is a huge productivity boost. Users can now run large-scale tasks (like codebase refactors or deep research) in the background. The CLI will orchestrate the agents without locking up the active terminal session.
Unified Architecture: The CLI shares the same backend agent harness as the new desktop app, Antigravity 2.0. This means any future improvements to the core agents will instantly apply to the terminal experience.

If you are looking for Gemini CLI, this is not the same as Antigravity CLI. Gemini CLI is the open-source version terminal interface that lets you use the power of the Gemini model for your tasks via natural language. It has its own ecosystem of Extensions and I have written a tutorial series on that earlier.

Blog Updates

04-Jun-2026 : Added section on understanding what changes have happened to Antigravity CLI via the agy changelog command. Added a new section on models subcommand introduced in 1.0.5 to get the current list of models supported and how to pass the model to the Antigravity CLI via the --model command-line parameter.

24-May-2026 : Added section on AGY CLI command-line parameters. Updated installation section with agy update command.

23-May-2026 : Updated the installation instructions. Added new sections on /btw command and /context command to visualize context.

Installation

The installation is straightforward and binaries are available across major Operating System. I have taken the commands to run in the terminal directly from the installation document:

macOS | Linux

curl -fsSL https://antigravity.google/cli/install.sh | bash

Windows PowerShell

irm https://antigravity.google/cli/install.ps1 | iex

Windows CMD

curl -fsSL https://antigravity.google/cli/install.cmd -o install.cmd && install.cmd && del install.cmd

This should ideally setup and install the Antigravity CLI (agy) in your system and in the Path.

For e.g. on my MacOS , the installer copied and setup the following executable here: /Users/romin/.local/bin/agyand there was an entry made in the profile to add that folder to the path.


# Added by Antigravity CLI installer
export PATH="/Users/romin/.local/bin:$PATH"

In some cases, if the installer is not able to add the binary ( agy to the PATH), it will say so. For e.g. on another machine, I saw the following output, where it will clearly tell you what to do, to add it to the PATH.

% curl -fsSL https://antigravity.google/cli/install.sh | bash
⠋ Detecting system environment...
✓ Platform detected: darwin_arm64
⠋ Querying release repository...
✓ Latest available version: 1.0.1
⠋ Downloading release package...
✓ Download complete and checksum verified.
⠋ Extracting binary from archive...
⠋ Configuring shell environment...
I0523 11:44:14.012088 76528 installer.go:27] Running Antigravity CLI setup...
Warning: /Users/neilirani/.local/bin is not present in your active PATH.
To use the 'agy' CLI globally, please manually add it to your shell profile:
  echo 'export PATH="/Users/neilirani/.local/bin:$PATH"' >> ~/.zshrc && source ~/.zshrc
✅ Antigravity CLI binary placed successfully at /Users/neilirani/.local/bin/agy
Note: The binary is installed, but it is not in your active PATH. Please follow the instructions above to add it, then restart your terminal session.

I suggest that we start with a specific folder agy-cli-projects and work through that for the rest of the tutorial.

Create a folder named agy-cli-projects and navigate into that. I have created it in my home folder but you can do that based on your preference.

Just check out the version of Antigravity CLI via the following command:

$ agy --version
1.0.2

Updating Antigravity CLI

You can update Antigravity CLI at any time via the agy update command. This checks for newer versions and then downloads and updates your current local installation.

Changelog

It is a good idea to check the changelog to get a sense of the updates that have happened across different versions of Antigravity CLI. Use the agy changelog command for that. A sample (partial) run for the latest update at the time of writing is shown below:

$ agy changelog
1.0.5:
· Added `--model` to set model when launching CLI. Also a new `models` subcommand to list available models.
· Added `/permissions` command which allows to add/edit/remove permissions rules for each of the three configs above directly inside the CLI.
· Allowed opening the Artifact Review panel (shortcut `ctrl+r`) while answering pending questions or tool permission confirmations, preserving your current progress when toggling back.
· Fixed a bug that metadata was written in the current directory as opposed to `~/.gemini/antigravity-cli/cache` when running using `-p`.
· Improved statusline layout by merging active tip and artifact status on a single line and truncating with ellipsis on narrow terminals to prevent collisions.
· Improved customization support by allowing directories in the customization manager to be passed as workspace directories, enabling correct trajectory metadata population and `/add-dir` support.
· Added support for `url` in `mcp_config.json` to configure MCP servers directly via a URL.
· Improved `/resume` performance: optimized lazy loading of conversation details, filtered out empty conversations, and added support for scanning SQLite database files (`.db` and `.db-wal`).
· Improved autocomplete: tab completion for slash commands now resolves to the matched alias instead of the primary command name (e.g., `/se` autocompletes to `/settings` instead of `/config`).
· Integrated the permissioning system with the rest of Antigravity. CLI permissions now merges project level permissions, permissions from user settings shared with Antigravity, and permissions from the CLI `settings.json`.

1.0.4:
· Added SQLite (.db) conversation support and will be CLI’s conversation format. Fixed a bug when importing SQLite conversation from Antigravity 2.0 to CLI.
· Added LaTeX math rendering, enabling the CLI to display beautiful mathematical formulas directly in the terminal viewport. Set `AGY_CLI_DISABLE_LATEX` environment variable to turn off LaTeX rendering globally if desired.
· Decoupled project discovery from local `.antigravitycli` workspace directories. The CLI now stores workspace-to-project mappings in a centralized `~/.gemini/antigravity-cli/cache/projects.json` file, eliminating repository clutter and speeding up project discovery to a single-map lookup.
· Resolved sporadic and permanent UI hangs caused by a stateful callback streamer race condition during network drops or extremely fast agent steps.
· Collapses all newlines and consecutive whitespaces in conversation previews and titles before rendering list items, preventing visual UI layout breaks in the picker rows.
· Styled the separator space between the line number column and diff content to match the text blocks, ensuring background highlights stretch seamlessly across the viewport width in tool outputs and `/diff` details.
· Resolved inconsistent behavior where selecting skill-derived slash commands from autocompletion suggestions cleared the input without executing. Autocompleted skill commands are now correctly submitted to the backend.
...

1.0.3: ...

1.0.2: ...

Logging into Antigravity CLI

When we launch Antigravity CLI for the first time, it will ask you to login. Launch agy and it should show something similar to this:


     ▄▀▀▄
    ▀▀▀▀▀▀
   ▀▀▀▀▀▀▀▀
  ▄▀▀ ▀▀▄
 ▄▀▀ ▀▀▄

 Welcome to the Antigravity CLI. You are currently not signed in.

 Select login method:
 > 1. Google OAuth
   2. Use a Google Cloud project

 [Use arrow keys to navigate, Enter to select]

Use your personal account for now. Choose 1. Google OAuth and press Enter. This will launch a browser and you can login with your Google Account. On successful authentication and authorization, you are asked to copy a code. Please come back into the Antigravity CLI terminal and paste the code.

Once the login is successful, a few things happen:

First up, it asks you about the color theme that you wish to choose for Antigravity CLI, as shown below. Pick the one that you like.

Next up, you need to accept a few terms of service:

Finally, the most important thing is to give your permission that you trust the folder, as shown below:

Accessing workspace:

/Users/romin/agy-cli-projects

Do you trust the contents of this project?

Antigravity CLI requires permission to read, edit, and execute files here.

> Yes, I trust this folder
  No, exit

  ↑/↓ Navigate · enter Confirm
                                                                                                                                   Gemini 3.5 Flash (High)

You will see this typically in any new folder that you launch the Antigravity CLI on. We will come to more on this later in the series but for now, go ahead and say Yes, I trust this folder.

You are all set now and its waiting for your prompt:


      ▄▀▀▄ Antigravity CLI 1.0.1
     ▀▀▀▀▀▀ <YOUR_ACCOUNT_EMAIL>
    ▀▀▀▀▀▀▀▀ Gemini 3.5 Flash (High)
   ▄▀▀ ▀▀▄ ~/agy-cli-projects
  ▄▀▀ ▀▀▄

───────────────────────────────────────────────────────────
>
───────────────────────────────────────────────────────────
? for shortcuts Gemini 3.5 Flash (Medium)

Antigravity CLI — A few housekeeping commands

Notice that it is using Gemini 3.5 Flash as shown in the bottom right. The first thing ideally is to understand that most of the customization and settings that you need to do are available via the /config or /settingscommand.

Configuration / Settings

Go ahead and invoke the /config command. This will bring up various areas of Antigravity that you can customize based on your preferences. This includes the Color Scheme, Tool permission, telemetry settings and more.

For example, the Color Scheme brings up the following options, from which I can choose my preferred color scheme:

settings.json

The configuration settings need to be stored somewhere right? All of them get stored in ~/.gemini/antigravity-cli/settings.json file. A sample is shown below:

{
       "colorScheme": "dark",
       "model": "Gemini 3.5 Flash (High)",
       "statusLine": {
         "type": "",
         "command": "",
         "enabled": true
       },
       "trustedWorkspaces": [
         "/Users/romin/antigravity-cli-projects",
         "/Users/romin/agy-cli-projects"
       ]
     }

You can notice the colorScheme that I have selected, the model and also various folders from where I have started Antigravity CLI and said yes to trusting the folders.

Note: You can modify the settings.json directly too and restart Antigravity CLI as a best practice to see the changes. But be sure of the settings, else it will display an error at startup. I suggest that given that the documentation is sparse at the moment, use the /settings or /config command in the Antigravity CLI to work with this file.

Tool Permission

An important setting to understand is the Tool Permission and I show the options below. You can get to this via the /config command.

Tool Permission
  > request-review (current)
    proceed-in-sandbox
    always-proceed
    strict

By default, it is set to request-review. Let’s understand this in more detail:

In Antigravity, Tool Permission settings control the balance between security (guarding your host system against unintended changes) and velocity (how autonomously the agent can work without pausing for your input).

request-review (Current Default)

In this mode, the agent is treated as a collaborative partner that checks in before performing any action that could affect your system or project files outside of pre-approved bounds.

How it works: Whenever the agent attempts to run a terminal command, perform a file operation (like writing/deleting), or call an external service where permission hasn’t been pre-approved, the execution pauses. The user is prompted to approve or reject the specific action.

Example:

The agent needs to install a package using npm install lodash.Instead of running the command immediately, the CLI pauses and shows a prompt as shown below, and you have choice to decide whether to allow it to proceed or so on. It is recommended that you can keep this default setting, so that you get familiar with how your commands are being run.

Requesting permission for: npm install lodash

Do you want to proceed?
> 1. Yes
  2. Yes, and always allow in this conversation for commands that start with 'npm install'
  3. Yes, and always allow for commands that start with 'npm install' (Persist to settings.json)
  4. No

proceed-in-sandbox

This mode allows the agent to execute terminal commands automatically, but within a secure, isolated container. The agent can run commands without prompting you, but those commands are executed in a virtualized sandbox (e.g., a lightweight container). They cannot modify your actual host machine’s filesystem or access your local network.

always-proceed

This is the fully autonomous mode, giving the agent maximum speed and capability. The agent is granted full permission to run commands and write files directly on your host machine. It will never prompt you for confirmation.

Example:

You leave a long-running task running overnight using the /goal command (e.g., “Refactor our styling system to use vanilla CSS and ensure all components build without error”). In this scenario, The agent writes dozens of files, runs npm run build , resolves compiler errors, installs helper packages, and runs git commands entirely on its own. The work completes without ever pausing to wait for your approval. (Use with caution: only use this in trusted, version-controlled repositories).

strict

This is a zero-trust, high-security mode. The agent’s capabilities are restricted to executing read tools. All non-read tools will require the user to be prompted for action.

Set a model

You can use the /model command to select a model that will be used. At the time of writing, this is the list of models shown when you use the /model command:

Switch Model

> Gemini 3.5 Flash (High) (current)
  Gemini 3.5 Flash (Medium)
  Gemini 3.1 Pro (High)
  Gemini 3.1 Pro (Low)
  Claude Sonnet 4.6 (Thinking)
  Claude Opus 4.6 (Thinking)
  GPT-OSS 120B (Medium)

Keyboard: ↑/↓ Navigate enter Select esc Go Back

You can choose any of the models as needed, based on your preference.

You do have an option of setting the model while starting a agy session. You can do that via the agy --model "model_name" command line options. This will then use a specify model for that session. This is very useful if you wish to start the agy session in an autonomous mode i.e. via the --prompt option. Take a look at the command-line options discussed later in this blog.

Antigravity CLI Reference (List of Commands and Shortcuts)

What are the commands and keyboard shorcuts Antigravity CLI. The command as expected /help is your friend. Alternately, you can just type a ? to get this list.

Try it out to see the range of commands available and learn a few shortcuts to navigate the terminal easily.

Here are all 34 commands available in 1.0.1 at the time of writing. Try out a few if you’d like. We will cover several of them as we go along in the series.

Changelog

Antigravity CLI is likely to undergo rapid changes. We saw that with Gemini CLI earlier, where there were almost daily updates. While we cannot predict the velocity of the releases, its good to know what is changing across the releases via the /changelog command. We are already seeing a good list of changes between the current version 1.0.1 vs 1.0.0 as shown below:

Exit Antigravity CLI

This can be done via the /quit command. If you are having difficulty to get to the prompt input, use esc esc to come out where you are.

Whenever you exit, you will see the command that is needed to continue the conversation. As an example, this is what I received. If you do that, you can resume the conversation and will have an entire list of prompts that you gave. Just use Arrows Keys (up and down) in the prompt to see the history.

Resume: agy --conversation=bbb2048c-7de6-4dd5-ba7e-8b0c27d46b95 (or -c)

Shell mode

This is similar to Gemini CLI and you can enter into a Shell mode, such that you can give shell commands without the need to exit Antigravity CLI and come back again to it.

Simply use the ! to go into Shell mode. You will notice that the prompt prefix will change from > to ! as shown below:

You can give commands like ls, pwd and other utilities that you might have too.

Our first coding task

I am going to create a folder inside of agy-cli-projects and start my Antigravity CLI inside of that. I have named the folder bq-release-notes since I am going to create a BigQuery Release Notes Reader application.

Let’s give Antigravity CLI our first task and ask it to build a web application that displays the content of a current RSS feed. Let’s say that I am very much interested in BigQuery Release notes. There is a RSS Feed for it.

I would like a web application in my prefered stack to be build to access this feed and show me the information.

I begin with the following prompt:

Please build a web application for me using Python Flask and plain vanilla HTML, JavaScript and CSS that fetches the BigQuery Release notes from (https://docs.cloud.google.com/feeds/bigquery-release-notes.xml) and shows them to me. A simple refresh button with a spinner is good enough, anytime I’d like to refresh the details. I would also like the ability to take any specific update, select it and then Tweet about it.

This results in the following response from Antigravity CLI:

  I will start by exploring the workspace to see if there is an existing structure or if this is a brand new project.                                                                    

● ListDir(/Users/romin/agy-cli-projects/bq-release-notes) (ctrl+o to expand)

  I will read the BigQuery release notes XML feed to understand its structure (Atom/RSS elements, entry/item elements, namespaces, dates, titles, content) so that we can parse it       
  correctly in the Python Flask backend.                                                                                                                                                 

● ReadURL(https://docs.cloud.google.com/feeds/bigquery-release-notes.xml) (ctrl+o to expand)

  I will view the fetched feed content saved locally to understand its format and structure.                                                                                             

● Read(/Users/romin/.gemini/antigravity-cli/brain/116191af-e6ea-4ba5-aa23-62f995bd068a/.system_generated/steps/6/content.md) (ctrl+o to expand)

▸ Thought for 2s, 2.3k tokens
  Analyzing XML Feed Structure
  I will write the implementation plan detailing the architecture, design aesthetic, components, and verification steps for the BigQuery Release Notes Web Application. This plan will be
  written to the artifacts directory.                                                                                                                                                    

● Create(/Users/romin/.gemini/antigravity-cli/brain/116191af-e6ea-4ba5-aa23-62f995bd068a/implementation_plan.md) (ctrl+o to expand)

  I have created the implementation_plan.md to outline the design and architecture of the BigQuery Release Notes Web Application.

  Please review the plan, especially the approach for the Twitter Composer & Preview Card, and let me know if you approve or if there are any adjustments you'd like to make!            

                                                                                                                                                            1 artifact · /artifact to review

Remember that behind the scenes, you get the same Antigravity harness and if you are familiar with Antigravity, you can see that it has created an artifact (file) for us to view. Artifacts are how the Antigravity CLI keeps us in the loop with an implementation plan, list of tasks that it is working on, verifiable outputs and more.

In this case, if you notice, it says and I quote “I will write the implementation plan detailing the architecture, design aesthetic, components, and verification steps for the BigQuery Release Notes Web Application. This plan will be written to the artifacts directory.”

Once it does that, it says “ I have created the implementation_plan.md to outline the design and architecture of the BigQuery Release Notes Web Application. Please review the plan, especially the approach for the Twitter Composer & Preview Card, and let me know if you approve or if there are any adjustments you’d like to make!”

You can see that it also mentions in the bottom right, that there is 1 Artifact to review and in this case, it is the implementation_plan.md.

Now remember, this is all in the terminal, so we will have to use that and see how it goes. It’s pretty neat if you ask me.

Give the command /artifact. This will display the following:

This clearly shows that there is a file implementation_plan.md created and I can use the arrow keys to open, approve, reject and so on. This should be familiar to those who have used earlier or even the recent version of Antigravity (the non-CLI app).

On opening it, I can see the entire artifact i.e. Implementation plan.

Just Escape and come back to the prompt, here you can approve it , if you’d like:

Alternately, you can reject or even converse with some changes or modifications that you like. For e.g. we will go full vibe mode and say approve.

This kicks off the next set of steps, where it will start the implementation i.e. creating files, running a few commans, etc. You will be prompted to approve and give permission to execute, as required.

In my case, I gave it the approval to create the Python virtual environment, install the dependencies via requirements.txt and so on.

In the background, it has also created a task.md file as part of the tasks that it has to do based on the implementation plan and it ticks off the individual tasks, as it completes them. You will just have to pay attention to the thought process and the tasks as it completes them. It makes for a fascinating experience.

Finally I get the message that I wanted to see:

I have successfully completed the implementation of the BigQuery Release Pulse web application!

The application dev server is up and running locally at http://127.0.0.1:5000.

Please refer to the walkthrough.md for details on the architectural implementation, the features we delivered, and verified test scenarios.

I also see that there are several artifacts as expected (Implementation Plan, Task List and a Walkthrough document)

Action required (3 left)
› task.md open 
  walkthrough.md
  □ new implementation_plan.md

  Media · 1 items (enter to expand)

If I look at the Task artifact, I get the following:

 task.md 
> 1 Tasks                                                                                                                                     
    2                                                                                                                                                
    3 [✓] Setup dependencies and environment                                                                                                     
    4 [✓] Implement backend Flask application ( app.py )                                                                                         
    5 [✓] Implement frontend HTML structure ( templates/index.html )                                                                             
    6 [✓] Implement frontend CSS styling ( static/css/style.css )                                                                                
    7 [✓] Implement frontend JS logic ( static/js/app.js )                                                                                       
    8 [✓] Verify local execution and manual test scenarios                                                                                       
    9 [✓] Create walkthrough documentation ( walkthrough.md )

Good work.

I check the application in my browser and here it is. It looks great with a lot of features already thought out:

Here’s my Tweet feature too:

I can go on now with new features, some changes, etc. But we can stop for now. The idea was to demonstrate and check out what it can do with simple requirements.

Our first non-coding Task

Go to https://github.com/rominirani/gemini-cli-codelab-projects and check out the folder invoice-processing folder that has several invoices in the form of images.

Let’s create a new folder inside of agy-cli-projects named invoice-processing. Download the four files into that folder and launch Antigravity CLI from there. You can take a peek into any of the invoices. One of the files is shown below (its an image):

You can use the Shell mode ( ! ) and then use the ls command to verify if you see the four invoice files there.

● ! ls
  ⎿ inv1.png
     inv2.png
     inv3.png
     inv4.png

Now give the following prompt:

Use @inv1.png and extract the following invoice information in the form of a table: Invoice No, Invoice Date, Invoice Sent By, Due Date, Due Amount.

Notice that you can use @ and you will see a list of files that will come up and you can choose from them. In short, I am asking Antigravity CLI to analyze this image file and extract relevant information of the invoice that I am interested in.

I get the following output:

  Analyzing Invoice Contents
  Here is the extracted invoice information from inv1.png:                                                                                      

   Invoice No │ Invoice Date │ Invoice Sent By │ Due Date │ Due Amount
  ─────────────────────────────┼─────────────────────────────┼─────────────────────────────┼─────────────────────────────┼────────────────────────────
    01234 │ 11.02.2030 │ Adeline Palmerston │ 11.03.2030 │ $440

I can even ask it to simply go through the folder and extract information from all the invoices present in the folder. Here is the prompt:

The current folder contains a list of invoice files in Image format. Go through all the files in this folder and extract the following invoice information in the form of a table: Invoice No, Invoice Date, Invoice Sent By, Due Date, Due Amount.

Here is the output:

Here is the extracted invoice information from all four files in the folder:                                                                        

   File │ Invoice No │ Invoice Date │ Invoice Sent By │ Due Date │ Due Amount
  ─────────────────────┼──────────────────────┼────────────────────┼────────────────────────────────────────┼────────────────────┼────────────────────
   inv1.png │ 01234 │ 11.02.2030 │ Adeline Palmerston │ 11.03.2030 │ $440.00
   inv2.png │ US-001 │ 11/02/2019 │ East Repair Inc. │ 26/02/2019 │ $154.06
   inv3.png │ 123456789 (P.O. #) │ November 23, 2023 │ A Company With A Clever Name (docubee) │ November 30, 2023 │ $42.30
   inv4.png │ [123456] │ 12/9/2019 │ Company Name │ 1/8/2020 │ $971.56

I could even go a bit different and ask it to highlight all invoices that are having payment date that has passed.

list all files with .png extension in this folder. Extract the invoice information from it by reading them locally and display it in a table format containing the following column headers: : Invoice No, Invoice Date, Invoice Sent By, Due Date, Due Amount. Add a column at the end of the table that shows a red cross emoji in case the due date is in the past.

Here’s the output:

I suggest that you go ahead and try out all kinds of tasks that are non-coding related. Analyzing some files, organizing them and so on.

Schedule an instruction

You can use the /schedule command to automate recurring tasks or set one-time reminders.

Let’s see how things work, when we just give the /schedule command. I get the following helpful reply:

/schedule

  Would you like to set up a recurring cron schedule or a one-time timer?                                                                             

  Please specify:                                                                                                                                     

  1. The timing: E.g., a duration in seconds (up to 900) or a cron expression (e.g., */5 * * * * ).                                                  
  2. The prompt: What task or reminder you want to run when it fires.

I go ahead and ask it to do a one-minute timer and then remind me that there is a meeting:

> A one-time timer

  For how many seconds (up to 900 seconds/15 minutes) should the timer run, and what reminder message (prompt) should be triggered when it fires?     

────────────────────────────────────────────────────────────
> In 1 minute, remind me that there is a meeting

○ Schedule() (ctrl+o to expand)

  I have set a 1-minute timer for you. I will notify you as soon as it fires.

Now, you can get back to your work with Antigravity CLI. Once the timer is up, it should fire and let you know. And yes , in a minute, I got this message:

 ⏰ Reminder: There is a meeting starting now!

Here are some examples:

A Pomodoro Timer that you can set and then get back to work. It will then remind you that time is up. /schedule duration=”600" prompt=”Remind me that the current task time is over”
In 3 minutes, run the following to check if migrations are successfully applied: /schedule duration=”180" prompt=”Run ‘npm run db:status’ to verify if all migrations were successfully applied.”
Here is one to check the logs in some time and see if there are any new errors: /schedule duration=”600" prompt=”Inspect the logs folder and check if there are any new error entries or uncaught exceptions.”

You can also do a recurring (Cron expression) schedule to do a task. For e.g. do something at 9:00 AM every monday, or every 12 hours, etc. Here are some examples (I recommend that you substitute it with your commands, utilities and specific instructions):

Standup Prep (Every weekday morning at 9:00 AM)

/schedule cron="0 9 * * 1–5" prompt="Generate a bulleted summary of all git commits and file modifications made in the workspace in the last 24 hours."

End-of-Day Code Quality Check (Every weekday at 5:00 PM)

/schedule cron="0 17 * * 1–5" prompt="Run 'npm test' and 'npm run lint' and report any test failures or code quality warnings."

Local Server Health Check (Every 10 minutes)

/schedule cron="*/10 * * * *" prompt="Check if the server running on http://localhost:3000 is still up and returning a 200 OK response."

Hourly Folder Scan (Every hour)

/schedule cron="0 * * * *" prompt="Scan the input directory for any new raw files, process them (put your rules here), and move them to the 'archive' folder."

Weekly Dependency Update Audit (Every Friday at 4:00 PM)

/schedule cron="0 16 * * 5" prompt="Run a security audit on project dependencies (e.g., 'npm audit' or 'pip-audit') and report any critical vulnerabilities."

As an example, I setup a one-time 10 minute timer and then another recurring timer than runs every 10 mins.

Once scheduled, I can interact in natural language with Antigravity CLI to find what tasks are running in the background. Just give a prompt like list my active tasks

> list my active tasks

● ManageTask(You have 2 background task(s) currently running:) (ctrl+o to expand)

  Here are your currently active background tasks:                                                                                                    

  1. task-35                                                                                                                                         
      • Type: One-time Timer (600 seconds)                                                                                                            
      • Prompt: "Remind the user that the current task time is over."                                                                                 
      • Start Time: 2026-05-22T20:26:11 (Local time)                                                                                                  
  2. task-43                                                                                                                                         
      • Type: Recurring Cron ( */10 * * * * — every 10 minutes)                                                                                      
      • Prompt: "Check if the server running on http://localhost:3000 is still up and returning a 200 OK response."                                   
      • Start Time: 2026-05-22T20:33:29 (Local time)

You can now interact with it to even remove a task and so on.

We have a lot more to cover

We have just scratched the surface at this point with Antigravity CLI. There are several commands to still try out, in addition to key things like configuring plugins, MCP Servers, skills, background tasks, parallel tasks, context management and more. Later parts of the tutorial will cover them.

Examine the Context

You can visualize your context at any point in time via the /context command. A sample is shown below:

By the Way (btw)

This is actually a command and a pretty useful one too. If you main agent is busy with some long running task, you can use the /btw command to ask it a side question. This does not interrupt the currently running task.

The best way to try this would be by giving the Antigravity CLI a long running task like generating some application and then while it is busy, just give /btw and see it in action.

For example, the Agent is in the midst of refactoring the code and you would like to know about a specific git command. Give this instruction:

/btw What is the git command to list branches sorted by last commit date?

or something like this:

/btw what does exit status code 137 typically indicate?

Here are few more things to know about /btw :

• Parallel & Non-Interruptive: If the agent is currently busy running a long build script or refactoring several files in the workspace, typing /btw does not pause, abort, or delay that process. The main agent task continues running in the background.

• Ephemeral UI: The output is rendered in a temporary overlay panel (similar to a modal) directly in the terminal interface. When you close the panel (by pressing Enter or Esc ), the response vanishes.

• No Side-Effects (Read-Only context): To ensure speed and safety, /btw operates in a read-only mode. It has full read access to the files and conversation state, but it cannot execute tools (e.g., writing files, running bash commands, or scheduling tasks).

• Token Efficiency: The prompt and response of a /btw query are not appended to the primary conversation history. This prevents casual questions from inflating the conversation context window (context bloat).

Understanding Command-line parameters of Antigravity CLI

When we launched Antigravity CLI, we simply used agy to launch it. It uses several defaults in terms of what it needs to do and then shows you the terminal in which you can proceed to give commands.

In this section, we shall look at a few command line options, that are available to use, while launching Antigravity CLI at the command line.

If you can’t wait, you can get the current list of command line parameters/options available to you by using the agy --help , agy help, or agy -h command. This shows the following list at the time of writing:

$ agy --help
Usage of agy:
  --add-dir Add a directory to the workspace (repeatable) (default [])
  -c Short alias for --continue
  --continue Continue the most recent conversation
  --conversation Resume a previous conversation by ID
  --dangerously-skip-permissions Auto-approve all tool permission requests without prompting
  -i Short alias for --prompt-interactive
  --log-file Override CLI log file path
  --model Model for the current CLI session
  -p Short alias for --print
  --print Run a single prompt non-interactively and print the response
  --print-timeout Timeout for print mode wait (default 5m0s)
  --prompt Alias for --print
  --prompt-interactive Run an initial prompt interactively and continue the session
  --sandbox Run in a sandbox with terminal restrictions enabled

Available subcommands:
  changelog Show changelog and release notes
  help Show help for subcommands
  install Configure environment paths and shell settings
  models List available models
  plugin Manage plugins (install, uninstall, list, enable, disable)
  plugins Alias for plugin
  update Update CLI

So far we have launched Antigravity CLI and have been using it in interactive mode. If you’d like Antigravity CLI to just take your prompt, execute it and give back the result., then go for the non-interactive mode. This is done via the --prompt parameter or via -p or --print parameter.

This can be very useful in scenarios where you want to integrate Antigravity CLI in automated pipelines or schedule something at a specific time, without the need for any human interface.

agy -p "What is the command line syntax for doing a GET call to myhost.com via curl"

This might be a good way to get some quick answers but do keep in mind that there is be no scope to continue the conversation with follow up questions.

If you like to live dangerously (I do not), then you can look for a very aptly named parameter called --dangerously-skip-permissions.

Launch Antigravity CLI via the following command:

agy --dangerously-skip-permissions

Then give the following prompt. Check that it did not ask me for any write file permissions.

> get the latest news and write it in a file called news.txt. Then create another file that contains the summary of that file.

● ListDir(/Users/romin/agy-cli-projects) 
● WebSearch(latest world news May 24 2026 news headlines) (ctrl+o to expand)

▸ Thought for 2s, 95 tokens
  Processing News Information

● Create(/Users/romin/agy-cli-projects/news.txt) 
● Create(/Users/romin/agy-cli-projects/summary.txt) (ctrl+o to expand)

  I have fetched the latest world news headlines and created the requested files in your workspace:                                                                   

  1. news.txt: Contains the detailed news headlines for today (May 24, 2026), including topics on geopolitics (U.S.-Iran negotiations, Ukraine conflict), U.S.  
  security incidents, the Ebola outbreak in Central Africa, and the passing of NASCAR champion Kyle Busch.                                                            
  2. summary.txt: Contains a concise, structured summary of the major categories covered in the news file.                                                         

● ! ls
     news.txt
     summary.txt

This mode can be useful in scenarios where things are local and in your control but still be prepared for surprises and hence use it with care.

Specifying a model to use for the session

You can use the --model parameter to tell Antigravity CLI to use a specific model during its session only. This is very useful for the autonomous mode that we discussed, where you would like to launch several agy sessions and use specific models for specific tasks.

But first, you need to know which models are available for Antigravity CLI. You can do that via the models subcommand as shown below:

$ agy models
Gemini 3.5 Flash (Medium)
Gemini 3.5 Flash (High)
Gemini 3.5 Flash (Low)
Gemini 3.1 Pro (Low)
Gemini 3.1 Pro (High)
Claude Sonnet 4.6 (Thinking)
Claude Opus 4.6 (Thinking)

You can use any of these model names to specify the model to be used for the session. You can do that via the --model command shown below:

$ agy --model "Claude Opus 4.6 (Thinking)"

Once Antigravity CLI launches, you can check either via the /model command about the specific model that you asked it to use or look at the bottom right that shows the model used for the session. An example is shown below:

More command-line options

We will cover c , continue , conversation parameters in a separate part in this series, but will keep adding more information on command line parameters here, as Antigravity CLI takes shape. If you’d like to learn more about Conversations, check out Part 2.

Transitioning from Gemini CLI to Antigravity CLI

If you have been using Gemini CLI, here are a few things that you need to understand.

First up, you are not going to lose any of favourite workflows. Antigravity CLI to a large extent retains most of the features that you have been used to from Gemini CLI. Since it is early days yet, it is expected that the product team will use this time to probably get more parity based on user feedback. When it comes to Antigravity CLI, note that at the start of the article, we highlighted its key points about parallel execution, shared backend harness of Antigravity 2.0 and faster execution times.

If you have been using a personal account with Gemini CLI, here are a few dates and events to keep in mind:

June 18, 2026: This is the hard cutoff for individual and free-tier users. On this date, the Gemini CLI and Gemini Code Assist IDE extensions will stop serving requests.

Please read the following blogs for more details on what will work or not, post June 18 2026 , especially if you are using a personal account.

An important update: Transitioning Gemini CLI to Antigravity CLI

It is also important to understand a few changes from Gemini CLI, especially when it comes to configuration files that you were used to editing while tweaking and setting things up. This is critical since you might be having Extentions, MCP Servers, Skills and Context files that you were using with Gemini CLI.

Check out this section of the document on Migrating , that helps you understand what Antigravity CLI can directly import and use and a few key differences.

Google Antigravity

Conclusion

Thanks for reading this tutorial. This is just an initial introduction to help maximum number of users get started with Antigravity CLI. I will cover more parts in detail, as we move along.

Google Cloud Platform Technology Nuggets — May 1–15, 2026

Romin Irani — Fri, 15 May 2026 04:50:41 +0000

Welcome to the May 1–15, 2026 edition of Google Cloud Platform Technology Nuggets. The nuggets are also available on YouTube.

Infographic for this post, generated by NotebookLM

AI and Machine Learning

Gemini 3.1 Flash-Lite is now generally available on the Gemini Enterprise Agent Platform. It is a model specifically optimized for ultra-low latency and high-volume production deployments. This addition to the Gemini 3 series focuses on providing precision for agentic tasks such as tool calling, orchestration, and automated pipeline execution while minimizing operational costs. Check out the blog post.

In a mid-cycle update of the Gartner® Magic Quadrant™ for AI Application Development Platforms, Google has been given the #1 ranking across the three use cases assessed in the associated Critical Capabilities report. Download a complimentary copy of the 2026 Gartner Magic Quadrant update here.

Data Analytics

While AI-powered SQL functions are a solid addition to the databases, cost and latency of these functions is a critical factor. An interesting approach called proxy models is now available, which are lightweight classifiers like logistic regression that replace the majority of expensive LLM calls during query execution. These models work by leveraging existing Gemini embeddings of data to identify semantic patterns, allowing the system to perform tasks like binary classification (AI.IF) or multiclass classification (AI.CLASSIFY) on the CPU rather than specialized hardware. The process involves an automated workflow where the engine samples a small portion of data, labels it using an LLM, trains a specialized proxy model on-the-fly, and evaluates its accuracy before deciding whether to use the proxy or the full LLM. This optimization is currently available in BigQuery and AlloyDB. Check out the blog post.

Databases

The Database Center has been infused with several AI-driven updates to assist with the management of large-scale database fleets. The platform now features Gemini-powered intelligence for fleet-wide performance analysis, a natural language chat interface for troubleshooting across services like Cloud SQL and Spanner, and a testing agent to validate the impact of recommendations on latency and throughput before they are applied. Technical enhancements include public APIs integrated with the Model Context Protocol (MCP) for developer tool integration, centralized slow query analysis, and the inclusion of BigQuery inventory and data affiliation to map dependencies between transactional and analytical systems. Check out the blog post.

Bigtable has introduced Bigtable in-memory tier, a new feature within the Enterprise Plus edition designed to provide sub-millisecond read latency by using a hybrid storage architecture. This tier utilizes Remote Direct Memory Access (RDMA) to transfer data directly from memory without involving the system’s CPU or operating system, which helps avoid performance bottlenecks during traffic spikes. It offers approximately 10x higher point read throughput per dollar compared to standard configurations and provides hotspot resistance by supporting up to 120,000 queries per second on a single row. Check out the blog post.

PostgreSQL 18 is now available in in AlloyDB alongside a new Extended Support offering for older versions. This update includes B-tree skip scans for faster data retrieval, parallel GIN index usage for JSON and full-text searches, and native UUIDv7 support for better indexing efficiency in distributed applications. The platform now allows for virtual generated columns to compute data on-the-fly without using additional disk space. For older versions ranging from PostgreSQL 14 to 17, Extended Support provides three additional years of critical security patches and bug fixes beyond the community end-of-life dates. Users can perform in-place major version upgrades to transition to these newer releases. Check out the blog post.

As always, if you are looking to bookmark a single link that covers whats new in Google Data Cloud, check this out.

Developers & Practitioners

The Gemini Enterprise Agent Platform is squarely focused on running, scaling, governing and optimizing agents in production. To do that, requires some key guidance from Google Cloud and that is now available in the form of 5 guides that help transition AI agents from prototypes to production:

Long-Running Agents: Utilize Agent Runtime for maintaining state up to seven days, enabling checkpoint-and-resume and human-in-the-loop approval workflows.
Agent Governance Stack: Implement a five-layer security framework using Agent Identity for isolation, Agent Registry for tool control, and Agent Gateway for policy enforcement.
Multi-Agent Orchestration: Use the Agent Development Kit (ADK) to build graph-based workflows and coordinator-specialist patterns for complex task management.
A2A and MCP Interoperability: Connect agents across organizations and data systems using Agent-to-Agent (A2A) and Model Context Protocol (MCP) standards.
Atomic Agent Blueprints: Access pre-configured architectures in the Agent Garden to accelerate development and avoid manual design errors.

Check out the blog post for more details.

While most of the AI developer tools focus on coding, one of the challenges that remains is that of the outer loop and bridging the gap between local development and production deployment. The Gemini CLI Extension for CI/CD is a tool that is designed to do exactly that. Using the Model Context Protocol (MCP), the extension integrates with Gemini CLI, Claude Code, and Antigravity to automate both “inner loop” tasks, like rapid deployment to Cloud Run via buildpacks, and “outer loop” requirements, such as generating cloudbuild.yaml files and provisioning infrastructure. Key technical features include a pre-deployment security scan to prevent secret leakage, an automated application analysis for containerization, and the ability to provision Artifact Registry repositories and Cloud Build triggers through natural language prompts. For more details, check out the blog post.

Containers and Kubernetes

Google Cloud has introduced an architectural update to Google Kubernetes Engine (GKE) that reduces node startup times by up to 4x to address cold-start latency. This improvement is achieved by reworking node provisioning logic through a combination of intelligent compute buffers, fast-starting virtual machines, and a control plane that allows for instant VM resizing without reboots. These technical changes aim to reduce the need for over-provisioning and improve the scaling of AI inference and batch processing workloads. The feature is currently available for GKE Autopilot and specific NVIDIA GPU hardware, including L4, A100, RTXPRO6000, and H100 nodes, as well as general-purpose compute. For more details, check out the blog post.

Security and Identity

Gartner has named Google a Leader in the 2026 Magic Quadrant for Cyberthreat Intelligence Technologies. You can download the full 2026 Gartner® Magic Quadrant™ for Cyberthreat Intelligence Technologies here.

The second Cloud CISO Perspectives for April 2026 is out. This issue discusses a strategy centered on multicloud and multi-AI environments to address modern security needs. Key technical highlights include the use of Gemini-powered security agents that have reduced alert triage times from 30 minutes to 60 seconds and a new dark web intelligence capability with 98% accuracy. The issue also discusses features in the new Gemini Enterprise Agent Platform, that has an Agent Gateway for identity management, Model Armor for prompt sanitization, and automated Agent Identity verification.

With the Wiz acquisition now complete and highlighted at Google Cloud Next 2026, most practitioners are looking forward to understand how it all comes together under a common platform. In the first Cloud CISO Perspectives for May 2026, the post highlights how the collaboration affects multicloud security and it discusses a strategy centered on developer enablement and automated defense. The collaboration combines Wiz’s cloud telemetry with Google Cloud AI logic to move toward near real-time vulnerability resolution and self-healing infrastructure.

If you are looking to understand the evolving security risks for AI coding agents, this article explains how the attack surface has expanded beyond source code to include the files these agents trust. Threat actors are now targeting repository-level artifacts like tasks.json, settings.json, and Skill.md files to execute code, exfiltrate API keys, or redirect traffic to malicious endpoints by manipulating the agent’s semantic intent. Because these files often use natural language or valid configurations, they bypass traditional signature-based scanners. To counter this, Google Cloud highlights the use of VirusTotal Code Insight to perform semantic analysis, allowing defenders to identify high-risk instructions and hidden supply-chain threats within developer environments.

Infrastructure

Google Cloud has introduced a cluster-level reliability framework for Tensor Processing Units (TPUs) designed to support the training of trillion-parameter AI models.

Storage

If you are looking to address storage bottlenecks in AI and machine learning workflows, you now have Cloud Storage Rapid, a suite of high-performance object storage capabilities designed for data-heavy workloads. This family includes Rapid Bucket, a zonal storage option that provides sub-millisecond latency and up to 15 TB/s throughput to keep accelerators like GPUs and TPUs saturated, and Rapid Cache, which increases read bandwidth for existing buckets without requiring code changes. Check out the blog post.

Write for Google Cloud Medium publication

Stay in Touch

Have questions, comments, or other feedback on this newsletter? Please send Feedback.

If any of your peers are interested in receiving this newsletter, send them theSubscribe link.

[Boost]

Romin Irani — Mon, 30 Mar 2026 11:23:30 +0000

Aryan Irani for Google Developer Experts

Mar 28

Reflections on my Trainings: Gemini for Google Workspace

#gemini #googleworkspace #livetraining #googleappsscript

6 min read