Wrong output- why is the output yes when it should be no

my flow is returning the wrong output in some cases:

https://www.gumloop.com/pipeline?run_id=TeoRvoE4wWdAy5UZCMtGbw&workbook_id=7BUKV3YnuwAjXsAPUKENQz&tab=2

line 82 is a website: sms-magic.com

the output should be no. there is a plan with “build your plan” CTA and no price, but it leads to a pricing page. but the output is a yes.

line 88 returns Error

Hey @danitbensimon! 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.

  1. Find your run link on the history page. Format: https://www.gumloop.com/pipeline?run_id={your_run_id}&workbook_id={workbook_id}

  2. Make it shareable by clicking “Share” → ‘Anyone with the link can view’ in the top-left corner of the flow screen.
    GIF guide

  3. Provide details about the issue—more context helps us troubleshoot faster.

You can find your run history here: https://www.gumloop.com/history

https://www.gumloop.com/pipeline?run_id=E6QywMN5XgFnwzNkfyZSbE&workbook_id=7BUKV3YnuwAjXsAPUKENQz

line 82 is a website: sms-magic.com

the output should be no. there is a plan with “build your plan” CTA and no price, but it leads to a pricing page. but the output is a yes.

line 88 returns Error

Hey @danitbensimon - You should add all these requirements in the AI prompt and then test and iterate using the subflow for a single input before looping it over your Google Sheet.

Here’s the subflow run link for the site you shared so you can view all the inputs and outputs of the nodes from the run log: https://www.gumloop.com/pipeline?run_id=Gi794Hb4qaffLXARiCuSFF&workbook_id=7BUKV3YnuwAjXsAPUKENQz&tab=2

More info on how to debug flows from the run log: https://docs.gumloop.com/core-concepts/run_log

But all the requirements already exist in the AI!! and it still doesn’t work. Im on this over 2 months now. this is really upsetting so much time has passed and this is not working!!

now i have another issue and its not working with this website: talend.com- https://www.gumloop.com/pipeline?run_id=nt8WzJ2UU3udtW258MEqHo&workbook_id=7BUKV3YnuwAjXsAPUKENQz&tab=2

Gotcha! Unfortunately, the best way to refine the output is by adjusting the prompt, experimenting with different models, and checking the inputs and outputs of each node. Since the Analyze Image node generates the final output, reviewing its inputs and tweaking the prompt is your best option.

You can check the inputs and outputs using the run log: https://docs.gumloop.com/core-concepts/run_log.

This topic was automatically closed 5 days after the last reply. New replies are no longer allowed.