## TL;DR
Stop the loop by checking the mail drafts and sent folders for an existing draft built from this demo summary before creating another, cap draft creation at one per summary, and require a human send decision so drafts cannot regenerate on a schedule by themselves. Start with the agent run history showing repeated follow-up drafts, the demo summary it sourced, and the send or draft log in the mail tool, work on one affected call, record, or run first, and prove the fix there before running the full set. Most cases clear once the cause named in step 2 is corrected at its source rather than retried unchanged.

```text
agent loop detected resending the same follow-up email draft from a demo summary
```

## Use this when
- You see this exact message or symptom: agent loop detected resending the same follow-up email draft from a demo summary
- One run, record, call, or object is affected and you can name it
- A retry without changing anything reproduces the same result

## Not for this skill when
- The system fails with a different message and none of the signals here appear
- Nothing has failed yet and you are doing first time setup or general planning
- Every service from this vendor is down for all users, which is a vendor outage to wait out first

## Steps
1. Reproduce the failure once using the agent run history showing repeated follow-up drafts, the demo summary it sourced, and the send or draft log in the mail tool, and record the time, the workspace or account, and the one item it names. Verify: you have one failing item identified, not a similar older failure
2. Inspect how many drafts exist for the same summary, what triggered each creation, and whether any completion check ran first. Verify: you can point to the specific value, field, segment, or state that does not match what this operation needs
3. Apply the fix at that source: stop the loop by checking the mail drafts and sent folders for an existing draft built from this demo summary before creating another, cap draft creation at one per summary, and require a human send decision so drafts cannot regenerate on a schedule by themselves. Verify: the corrected value or setting is visible in the system itself, not only in a local file or the agent notes
4. Re-run the original operation on the single affected item first. Verify: that one item completes with no trace of the failure described above, and one draft exists for the demo summary and a rerun creates no additional copy
5. Check the downstream result a user or the next job would see, comparing it against the source for the same item. Verify: the downstream result agrees with the source in content and in timing
6. Repeat for the full set, watch the first few items in the same log you started from, and write the root cause and the changed setting into the run notes. Verify: the full run finishes, the notes name the failure and the fix, and no earlier item regressed

## Variant phrasings
### agent loop detected resending the same follow-up email draft from a demo summary
The subject-first phrasing of the same failure. The fix is the same, start at step 1 and confirm the item the log or record names.
### Tool-first phrasing of this failure
The phrasing searchers use once they know which system raised it. It is the same underlying problem, not a separate bug.
### Why does this keep happening after a retry
The repeat-occurrence phrasing. A retry without the step 2 and step 3 checks almost always reproduces it, because the cause sits in the input, setting, or record state, not in the attempt.

Compatibility: Agent workflows drafting follow-up mail from call summaries, at current versions

## Why it happens
A loop forms when the agent treats a saved draft as unfinished work and the trigger stays true, so each pass creates the same draft again instead of seeing the task as done.

## Provenance

Resolved from the public thread: https://vectle.com/posts/pst_OBKZTyYDb_wzKS8zrmM_RA