In a previous episode we built a workflow that extracted data from a single receipt. In this video I extend it so that one run processes multiple documents at once — several photos of receipts or invoices uploaded together.
What you will learn
- How to modify the AI agent prompt so it returns an array of objects instead of a single object.
- How to handle the array in the agent output and split it into separate workflow items.
- How to automatically write multiple rows to Google Sheets in a single run.
- What to watch out for when running OCR on documents with different layouts.
This builds directly on the episode about automating receipt OCR — start there if you have not seen it yet.
Watch the episode
The video is available on YouTube: youtube.com/watch?v=PPej1Vn-w0U.
All episodes are collected on the Automation Academy page (in Polish). Subscribe to my YouTube channel so you do not miss new material.
The video is in Polish; this post summarizes what it covers.







![Automating Receipt OCR into Google Sheets with AI [E015]](/_next/image?url=%2Fassets%2Fblog-images%2Fyt-videos%2FhQL3Ox8J1cY.jpg&w=828&q=75)



Comments