How to Trigger a Copilot Agent from Power Automate to Process PDFs and Generate CSV Output?

(0) Share

Report

Posted on by CU17041324-0

Hello everyone,

I’m trying to build a workflow in Power Automate and I’d like to know the best way to integrate a Copilot agent into it.

My goal is the following:

when a file is dropped into a folder or a SharePoint library,

Power Automate automatically triggers,

then launches an AI / Copilot agent that reads and processes a PDF,

the agent returns structured text as output,

and finally I use Python to transform that text into a CSV file.

I would like to understand:

what is the best way to trigger a Copilot agent from Power Automate after a file is added to SharePoint or a folder,

whether the agent can directly read and extract information from a PDF inside the workflow,

how to pass the agent’s output back into Power Automate in a clean text or JSON format,

and what is the recommended way to connect that output to a Python step for CSV generation.

If anyone has already built something similar, I’d really appreciate:

an example architecture,

the right connectors/actions to use,

and any limitations or best practices to be aware of.

Thanks in advance for your help.

Categories:

AI Builder

I have the same question (0)

All responses (2)

Answers (0)

Sort by

Suggested answer

Vish WR 3,507 on at

Like (0)

Report
Copy link

Link copied!

@CU17041324-0

You can achieve this with Power Automate using the SharePoint trigger along with AI Builder (Document Processing), and built-in data operations, without requiring a separate Copilot agent.

High-Level Flow Approach:

1. Trigger: When a file is created (SharePoint / OneDrive)

2. Get file content

3. AI Builder: Extract information from documents (prebuilt or custom model for PDFs)

4. Parse output (JSON) using the Parse JSON action

5. Transform data using Select or Compose

6. Create a CSV table (built-in action)

7. Save the CSV back to SharePoint or OneDrive

Reference
https://www.youtube.com/watch?v=J3d6bx3i4l0

https://sharepointlessons.wordpress.com/2020/08/27/using-ai-builders-form-processing-model-and-flow-to-extract-data-from-pdf-files/

Vishnu WR

LinkedIn - My Tech Space

Please ✅ Does this answer your question if my post helped you solve your issue. This will help others find it more readily. It also closes the item. If the content was useful in other ways, please consider answering Yes to Was this reply helpful? or give it a Like ♥

Was this reply helpful? Yes No
CU19050456-1 10 on at

Like (0)

Report
Copy link

Link copied!
Hi @Vish WR,

I am currently using a similar approach to address the invoice processing requirements. However, I am facing challenges with extraction accuracy, which is currently around 55% for the overall process in production.

The primary challenge is that we receive multiple types of documents and a large variety of invoice formats (approximately 100+ different formats/vendors). Due to these layout variations, OCR extraction quality and field mapping consistency are significantly impacted.

I would appreciate your suggestions or recommendations regarding:

Improving extraction accuracy in “Get text from document”

Best practices for handling multiple document formats

Any available documentation, benchmarks, or references related to AI Builder OCR accuracy

Recommended approaches for scalable invoice-to-JSON extraction

Any guidance or production learnings would be very helpful.

Thanks in advance.

Was this reply helpful? Yes No