is anyone else having issues with the support page. I’ve been trying to access the guide on ‘Analyze media’ trigger as it’s not working for me in my Ai agent build
oh thank you, I’m trying to build an agent that processes image receipts and PDFs for business expenses and then organizes them into folders. Here is a screenshot of the workflow and the error messages. The test resulted in the AI hallusinating the data from the PDF and it seems like the ‘Analyze media’ is not capturing or transferring the bytes to the next step. Note: when it says ‘exit loop’ that ‘canva’ data is incorrect. Am I missing a step inbetween Enter loop and Analyze media ?
I tried the agent builder and this is the solution it suggested “Google Drive: Get File By ID” When I tried this it’s still not processes the receipt correctly.
Hey Daniela! Happy to take a look - Do you mind sending over the task URL for these examples? How to share your Lindy task URL: 1. Click your Lindy agent → click “tasks” 2. Find the task you need help with 3. Click the specific task (you should see the full execution) 4. Copy that page URL from your browser 5. Paste the URL in your support request Note: The URL should include “task” followed by a number 💡 Screenshots are also helpful!
https://chat.lindy.ai/share/new-file-notification-6966dfb73e6decba49ebbc5a For context the data should say: Anthropic subscription $34 AUD 11/01/2026 The agent is saying: Canva $49 on 27/11/2025
wondering if there is an update on this support item
Hey Daniela -- Apologies about the delay! I would try using the 'Extract Webpage Text' action instead. It may work better in a situation like this! I would also replace the variable inside of the analyze media/extract webpage text file to a variable from the previous step that is the Get File by ID action instead of the loop action!
Please do let me know if that helps 🙏
No sure I understand, I will try this today and report back if it works. I tried to find in the Lindy docs about the ‘Analyze media’ function and could not find information on it. I’m hoping the agent can read images such as PNG or JPEG files (besides PDFs)
