Does this mean that the AI model was down? I have had this type of error happen for ask AI nodes before. Now, I just had it fail 8 times (webhook triggered runs).
If so I might add another AI node with different model for whenever there’s an error for the first one. (It might be a cool feature to allow the same node to automatically use a different selected model when this type of error happens)
Hey @SimonSays! 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 @SimonSays! You’re right—the model did time-out here (just a case of service overload). There’s nothing wrong with the workflow itself, and this error is transient. It resolves on its own within a few minutes once the model provider’s service is back up.
The best approach would be to use the ‘Ask AI’ node with an error shield enabled. You can turn on “pass inputs through on error” and use a backup AI node to catch those cases.
Let me know if that makes sense and works for you. It would definitely be cool to have this kind of auto-backup feature—I’ll add it to the roadmap to explore.
