# Tessary RCA

RCA is the explain step at the end of Tessary's pipeline. By the time it runs, the cheap classifiers
have swept every trace and recorded findings, triage has ruled which of those findings are real
deviations rather than legitimate changes, and the real ones have become a case. RCA runs on that
case. Its job is attribution: saying why the deviation happened.

Each run is an agentic session in a fresh E2B microVM with the connected repo. It investigates the
failing cohort with three inputs: the trace evidence, a dossier of what's known about the case, and
the code itself.

The output is a set of grounded hypotheses for the cause, each with the evidence behind it, plus the
checks the investigation ran and ruled out, so engineering doesn't repeat them. The report cites the
files involved.

After attribution, RCA raises a PR with the fix.

## Questions answered under this concept

- [Does Tessary fix the regression itself?](https://tessary.ai/answers/tessary-rca/does-tessary-fix-the-regression-itself)
- [Does Tessary need access to my repo to find the root cause?](https://tessary.ai/answers/tessary-rca/does-tessary-need-repo-access-to-find-the-root-cause)
- [Is RCA turned on by default?](https://tessary.ai/answers/tessary-rca/is-rca-turned-on-by-default)
- [What happens after Tessary confirms a case?](https://tessary.ai/answers/tessary-rca/what-happens-after-tessary-confirms-a-case)
- [What is a root-cause report?](https://tessary.ai/answers/tessary-rca/what-is-a-root-cause-report)
- [Why does a root-cause report list more than one possible cause?](https://tessary.ai/answers/tessary-rca/why-does-a-root-cause-report-list-more-than-one-hypothesis)

---

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