Hi team, can somebody help me please with my automation. I’ve got 2 tables of data:
Google Sheet 1 with all customer responses where each column represents a question that is being asked and everything underneath is the answer that depends on a multiple choice selection.
Google Sheet 2 which has all the potential answers and its corresponding recommendation to what customer should be doing.
So sheet 1 has a horizontal alignment and Sheet 2 has a vertical alignment.
What I would like to do is to automate the report that is full of recommendations once customer has submitted a survey.
I used googl sheet reader for both, followed by the combined list functions, followed by variations of either ask ai or extract data nodes + millions of other variations, but for some reason I can’t just automate that match function where each response is matched to recommended suggestion. So I can generate the report and email it to the client. Any suggestions please? I’m trying to get this sorted ASAP for the public demo we’ll be hosting and it’d be powerful to demonstrate the power of automated AI.
Hey @Misha_HarnexAI! If you’re reporting an issue with a flow or an error in a run, please include the run link and make sure it’s shareable so we can take a look.
Find your run link on the history page. Format: https://www.gumloop.com/pipeline?run_id={your_run_id}&workbook_id={workbook_id}
Make it shareable by clicking “Share” → ‘Anyone with the link can view’ in the top-left corner of the flow screen.
Provide details about the issue—more context helps us troubleshoot faster.
Hey @Misha_HarnexAI - I’d recommend using a Combine Text node to format all the data with context so the AI can properly identify the inputs and respond to your prompt.
You can use the run log to check what inputs each node gets and see if that makes sense WRT to your use case. Guide on using the run log here: https://docs.gumloop.com/core-concepts/run_log
Let me know if this makes sense and works for you.
Love it! Thank you Wassay! I didn’t know that join list can be used in such ways. Really appreciate it and looks like this would be awesome usecase we’d be able to demonstrate to wider audience!