Nutrient

Most teams already extract data from KYC files and bank statements. The trouble is what comes out the other side: a value with no confidence score and no link back to where it sits on the page. Would you sign off on data you can’t trace? Before that output moves into onboarding or a loan approval, teams need answers: → Can a reviewer verify where the data came from? → What happens when information is missing or conflicting? → When should automation pause for human judgment? That’s the conversation we’re bringing to Money20/20. Visit Nutrient at booth 21092 at the Venetian, Las Vegas. Which step in your document workflow would you still want a person to sign off on?

Story time: we gave our extraction a four-page California small claims form, and it came back with the currency as "USD," even though those three letters appear nowhere in the document. The form is a real court form filled in with test data, and we'd asked for six things: - The plaintiff - The defendant - Amount claimed - Currency - Date of the incident - Reason for the claim Five of them were right there on the page. The currency wasn't, but our setup mentioned that US court forms always use dollars, so the model did the sensible thing and filled in USD. It wasn't really wrong, but it was a guess rather than something read off the form, and in the extracted data it looked exactly like the five values that were. If you're automating claims, contracts or court filings, that's the kind of answer that slips through until someone has to explain where it came from. We caught it because every value comes back with a citation showing the page it came from and the exact spot on that page. The currency pointed to a different page from the amount it belonged to and scored noticeably lower, so a review step would send that one field to a person and let everything else through. And that's really what we want from AI on such documents. It doesn't have to be perfect, but it does need to alert a human when it is not exceptionally confident in a result. Remember, you are responsible for every document you submit - whether AI assisted or not, so you better be sure that it is correct. Don't play AI roulette. #DocumentAI #DataExtraction #AI

A picture of a signature on a PDF doesn't tell anyone whether the contract changed after it was signed. A digital signature does, because any later change to the signed content shows up when the file is checked. How to add one with Nutrient API: https://bit.ly/4s7esrM

🎰 Place your bets: what’s holding back AI in your financial document workflows? Reading a KYC file or bank statement is one step. Verifying the output, handling exceptions and keeping an audit trail are where teams get stuck. Vote below. We’ll share the results at Money20/20, booth 21092 at the Venetian Las Vegas.

Building on the Nutrient Data Extraction API is a breeze. Our customer came to us with a problem: they receive invoices from all across the globe. Different languages, different currencies, and each one checked by hand. Not anymore. In less than 30 minutes, we built them a custom app that identifies discrepancies, and notifies their accounts team when something needs their attention. All built inside of Claude using only natural language. #sdk #documents #aidocs #artificialintelligence

An expense report can spend far more time waiting in inboxes than it ever spends being reviewed. It goes to a manager, then finance, then a VP if it's over $10,000, and every handoff is another inbox where it can sit over a weekend while the contract waits to be paid. Nutrient Workflow sends it to the right person the moment it's submitted, nudges reviewers automatically, moves it to a backup approver if someone doesn't act in time, and pushes the approved numbers into your finance system so nobody retypes them. We save you time, and time is money. #WorkflowAutomation #Operations #Productivity

Agents don’t squint at a scan. If OCR drops a digit or shifts a value one row down in a table, the agent acts on it with full confidence. That’s why I don’t think “how accurate is your OCR?” is the right question. Ask whether every value can be traced back to where it sits on the page, and whether the uncertain ones get flagged for a human. Our team compared nine OCR APIs, including ours, on outputs, integration, and cost. It’s built from public documentation, not a benchmark, so test the finalists on your own ugliest documents. #OCR #DocumentAI #AIAgents #IntelligentDocumentProcessing #DataExtraction

It's only a matter of time before a major incident gets blamed on a mistake made by an AI agent, and "the AI did it" is an excuse nobody is going to accept. Each of us is responsible for what our agents produce. That makes auditability more important than it has ever been, especially now that AI is drafting redlines, discharge summaries, and responses that people then sign off on. With Nutrient Document Authoring, each AI suggestion lands as a tracked change with a comment explaining it, so a human is always aware of what is happening, and can approve changes on a case-by-case basis. An instrumental tool in high leverage situations. Call it CYA for the age of AI agents. The AI won't be the one sitting in the incident review when something goes wrong, but you will, so bring the receipts. #LegalTech #AIGovernance #DocumentAutomation

If you can't trust your OCR some of the time, can you trust it at all? OCR (optical character recognition) turns a scan or photo of a page into text your software can use. Clean, typed pages are a breeze. But just one problem... Real documents aren't always clean. A rotated scan, small print, a long table, a handwritten form: that's where a number gets misread or lands in the wrong row. And the response still looks fine. Your agents can't tell, and if you aren't looking closely, you won't notice either. Yet, someone has to sign off on all of this. So the question isn't whether OCR works on an easy page. It's whether you can tell when it got something wrong. We compared nine OCR APIs, including our own: what each one returns, what it takes to integrate, what it costs, and how to test it on your hardest documents. It's based on public documentation, not a benchmark. Where Nutrient fits: we link extracted content back to where it appears on the page and mark the values that need a second look, so your team knows what to check. #OCR #DocumentAI #DataExtraction

For nine days in April, our monitoring vendor had our metrics switched off, and the only reason we noticed was that our dashboards looked suspiciously calm. There was no email or status-page notice, no alerts. And losing metrics silently can be worse than a clear outage because alerts can't fire on data that never arrives. We closed that account, and because everything was already instrumented with OpenTelemetry and routed through collectors we run ourselves, moving terabytes of telemetry to a new vendor took a handful of config changes and no application redeploys. The lesson for businesses is simple. Build on the standard, not the vendor, and pivoting will cost you very little. https://bit.ly/4eibquR #OpenTelemetry #Observability #DevOps