Claygent Prompt Down for 2 Weeks: Urgent Support Needed | Clay

Claygent Prompt Down for 2 Weeks: Urgent Support Needed | Clay

Clay Support
APP
·
·
That's incredibly frustrating—infinite re-runs causing doubled API costs is a serious issue that needs immediate attention.
For the infinite re-runs specifically, recent updates to Claude Sonnet 3.7 integration have changed token usage patterns, and we're deploying features like retries and smarter pacing to handle rate limits better.
Since you've isolated this to one prompt and done extensive troubleshooting, try using Sculptor (top-right corner) to rebuild the prompt from scratch—it can generate fully structured prompts that may resolve the infinite loop issue.
If Sculptor doesn't resolve it, ask to speak to a human for immediate engineering escalation given the client impact and API cost issues.
Clay Support
APP
·
·
Is that what you were looking for?
Colin G.
·
·
Here’s the full context: What’s happening:
A previously stable Claygent prompt now fails 100% of the time
It either hangs indefinitely at “molding/sculpting/calibrating”
Or returns fallback errors like: “Unable to retrieve current employment information from LinkedIn”
This started suddenly — the prompt worked fine for 7 months before this
Critical context:
The exact same LinkedIn URLs succeed in other Claygent prompts
All prompts are in the same Airtable table, using the same API key and GPT-4o Mini model
This is isolated to one prompt only — every other prompt with the same setup is working
What we’ve already done (repeatedly):
Fully rebuilt the prompt from scratch (not duplicated)
Removed all conditional run logic
Switched output format from Fields → JSON Schema
Simplified the prompt structure and fallback logic
Cleaned and standardized all output field names
Tested with known-good profiles that work elsewhere
Tested from multiple devices, users, IPs, and regions
Why this needs escalation:
We’ve been told we’d get an update — we never received one
This issue has now gone unresolved for 2+ weeks
A client has already paid for 2 weeks of GTM services we couldn’t deliver because of this
Claygent appears to be glitching and re-running the prompt on its own, which has doubled our API costs (~$500/week)
Our ask:
Escalate this to engineering immediately
Inspect backend execution logs for the failing prompt
Confirm where the job is failing (dispatch, scrape, parse, etc.)
Reset or recompile the prompt object if needed
We can share prompt IDs, test data, and screenshots privately — but this can’t continue. We’re completely blocked. cc Sayudh M. John D.
Clay Support
APP
·
·
I'm sorry to hear about the ongoing issues and the impact this has caused. I’m routing you to our human team now so they can assist you further.
Clay Support
APP
·
·
Our support team has got your message and we'll get back to you soon!
If you’re dealing with a specific table, drop the URL below so we can help you quicker. Otherwise, someone from our team will be in touch soon!
image.png(93 kB)
Colin G.
·
·
https://app.clay.com/workspaces/42993/workbooks/wb_0t5km3syPmFkm5kcTWk/tables/t_0t7bi92cvB4cAhuoM8R/views/gv_0t5ogpyFtbYhuwGMKBU
Ethan Huang
APP
·
·
Thanks for reaching out! Colin - Sorry for this, it looks like we've got a bug on our hands. I've escalated this to our engineering team to help look into it. We'll follow up here as soon as we know more!
Ethan Huang
APP
·
·
Hi Colin, seems like you may have been getting rate-limited. Did you get this one figured out?