# Cause attribution

Cause attribution is the step from "quality dropped" to "this specific change caused it." Detection
establishes that a regression happened; attribution names the change responsible. Knowing a
regression exists still leaves the whole search for where it came from. That search is what
attribution does.

Any regression has a finite set of candidate causes: a code commit, a prompt edit, a model change, a
tool whose behavior shifted, or an upstream system the agent depends on. Attribution is an
investigation over that set. You gather the failing traces into one cohort, line up the onset of the
failure against the change history, and test each plausible candidate against the evidence in the
traces until the ones that don't hold are ruled out.

Localization is what makes the search tractable. Failures cluster around the code path that produces
them. When the failing traces share one path and the failure started at a known time, the candidate
set shrinks from everything shipped recently to the handful of changes that touched that path in
that window.

A finished attribution is a grounded explanation: the named cause, the failing traces and findings
that support it, and the hypotheses that were checked and ruled out. Because the cause is a specific
change in a specific place, the attribution also says where the fix belongs.

## Questions answered under this concept

- [How do I find out which change caused my agent's quality drop?](https://tessary.ai/answers/cause-attribution/how-do-you-find-which-change-caused-a-quality-drop)
- [How do I tell which deploy was live when a session failed?](https://tessary.ai/answers/cause-attribution/how-to-find-which-deploy-was-live-during-a-failure)
- [What evidence should a regression investigation include?](https://tessary.ai/answers/cause-attribution/what-evidence-a-regression-investigation-needs)
- [What comes back when the cause of a failure cannot be established?](https://tessary.ai/answers/cause-attribution/what-happens-when-no-cause-can-be-found)
- [Why did a downstream agent get worse when its own code never changed?](https://tessary.ai/answers/cause-attribution/why-a-downstream-agent-breaks-with-no-code-change)
- [Why doesn't an alert that reports a score moving help me?](https://tessary.ai/answers/cause-attribution/why-doesnt-a-score-alert-help-me)

---

Source: https://tessary.ai/answers/cause-attribution
All concepts: https://tessary.ai/answers
From Tessary, agent reliability for AI agents in production: https://tessary.ai