👤 For pipe admins
🔐 Available on all plans
🎯 For those who want to use the power of artificial intelligence to read documents and extract information automatically within their processes.
The Intelligent Document Processing (IDP) feature was developed to improve the accuracy of AI Agents in one of their most common uses: automatically extracting data from attached documents (such as invoices, contracts, receipts, etc.).
This enhancement combines AI Agents’ intelligence with OCR (optical character recognition) technology, making the reading and extraction process much more accurate, especially for complex files or those with diverse formatting.
🚀 How does it work?
The Intelligent Document Processing setting is activated within a specific Behavior of your AI Agent. This is an advanced tool that improves the agent's ability to read and extract data from files attached to the card.
Follow these steps to activate it:
In your pipe header, click the new AI Agents tab
Create a new AI Agent or click an existing one to edit it
Inside the agent, go to the Behaviors section
Create a new behavior or click an existing one to open its settings
On this behavior's configuration screen, scroll down to the Advanced tools section
Turn on the Activate Intelligent Document Processing toggle.
This example shows a behavior called 'Invoice Processing'. By activating 'Intelligent Document Processing', the agent can read the file attached to the 'Invoice' field, Update 7 card fields with the extracted data, and if the invoice is due this month, Create a card in Payments.
⚠️ Attention: What's the difference between "Intelligent Processing" and the "Documents" skill?
While both features read documents, they have different purposes:
Intelligent Document Processing (this article):
What it does: Extracts data from files (PDF, PNG, JPG) that are dynamically attached to a card.
Example: "Read the attached invoice on this card and fill in the 'Total Amount' and 'Due Date' fields."
"Documents" within the Knowledge Base:
What it does: Consults a fixed document (like an internal policy or manual) that you upload in the skill's configuration as a knowledge base.
Example: "Consult the product manual and check if the customer's requested item is eligible for a return."
💳 How credit consumption works with Intelligent Document Processing
Whenever an AI Agent performs document data extraction with the Intelligent Document Processing feature enabled, the consumption will be:
2 standard AI Agent credits
+1 additional credit for OCR (IDP)
Total: 3 credits per run involving document reading.
For more details on standard AI Agent credit usage, see "How AI Agents pricing works".
Applied limits: follow the same general AI Agent limits:
Maximum of 30 documents or images per run (e.g., 30 pages in a single file, 2 files with 15 pages each, 3 files with 10 pages each, etc.).
More details on the "AI Agent: Create an Agent" article.
🧠 Why use it?
Significantly higher accuracy in extracted data, even from documents with varied formatting;
Ideal for critical use cases such as reimbursements, accounts payable, contract validations, and more;
Reduces rework and prevents errors in automated processes.
📌 See also: