A tool's input and output are each defined by a JSON schema, and every run is validated against both: the caller's record against the input schema before the tool runs, and the result against the o...
Deleting a tool moves it to the recycle bin, where it stays for 30 days — or until your data retention policy removes it — before it's gone for good. You can't delete a tool while any flow, API, AI...
Downloading a tool packages it, with every nested tool, lookup, import, and script it uses, as a zip file you can keep, share, or upload into another account or environment — for example, to promot...
Moving a tool changes which integration it belongs to without copying it — the same tool, with the same references from flows and agents, appears under a different integration. Use it to gather sha...
Cloning creates an independent copy of a tool — with every nested tool, lookup, import, script, lookup cache, and custom API it uses — in the integration and environment you choose. Use it to make ...
Overview When an AI agent can't read a document, the record fails with a message on the flow step's Errors page, in the run console, and in the agent's preview. When the agent reads the document bu...
You can automate purchase orders from trading partners that send orders as PDF or spreadsheet files — by email or file upload, instead of EDI — with a flow that reads each order with intelligent do...
OverviewYou classify documents in integrator.io with an AI agent that reads each document and returns its type from a list you define. A branch then routes each type to its own extraction agent and...
Data extracted from documents in integrator.io passes through three layers of checks before it reaches a destination: Celigo validates the AI agent's response against your schema, the agent flags v...
OverviewWith intelligent document processing turned on, AI agents in integrator.io read native and scanned PDFs, Word, Excel, PowerPoint, and RTF documents, TIFF and BMP scans, images, and plain-te...