Read, parse, and convert documents with PDF.co, with edits held for approval
Operations teams end up with PDFs in the loop: scanned change forms, vendor invoices, exported reports. Connect PDF.co and Luumen can read a document's metadata, search its text, and pull structured fields out of it on the spot. Conversions, OCR passes, and edits to a file run as previewed steps you approve first. Access uses an API key.
34 tools: 17 read, 17 write. Reads answer instantly. Writes require approval by default. Everything is logged.
What a governed PDF.co run looks like inside Luumen.
Authorize once with API token. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.
Read actions answer immediately. Anything that writes — convert excel to csv, convert excel to html, convert excel to json, upload file, and more — is shown as a plan and requires approval by default. Administrators configure that per tool, so you decide exactly which actions can ever run unattended.
You decide. Actions are granted per agent, skill, and team, and per environment — production is not staging. Read access can be broad while writes stay narrow.
Every call to PDF.co — read or write, approved or declined — is recorded with the actor, the input, and the result, and can be linked to the ticket or change record.
Connect in minutes. Every action scoped, approved, and audited from day one.