Audit advanced Works with: Any AI

CI Pipeline Failure and Flaky Test Log Audit

Table output

Review pasted CI run history and logs to separate flaky tests from real failures and slow steps, with a prioritised repair list.

The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.

[VERIFY] is an editorial flag, not a blank to fill. Wherever the prompt shows [VERIFY], check that item against a reliable source before you use it.

You are helping me stabilise the CI pipeline for [PROJECT_NAME]. I will paste a summary of the last [NUMBER_OF_RUNS] runs: run id, branch, result, duration, and the name of any failing job or test: [RUN_SUMMARY]. I will also paste log excerpts for the three most common failures: [LOG_EXCERPTS]. Our CI tool is [CI_TOOL].

Report: 1) Overall pass rate, and the pass rate on main compared with feature branches, with the arithmetic. 2) A table with the columns Failing test or step, Times failed, Times it passed on re-run, Classification (probably flaky, probably real, infrastructure, unclear) and Evidence. 3) The slowest steps and what share of total run time each takes. 4) A repair list ranked by developer time wasted, which is failure count times average re-run time, with the calculation shown. 5) Habits to reduce waste: quarantine policy, retry limits, timeouts, test isolation.

Rules: classify only from the data pasted; if a log excerpt is too short to judge, say so and tell me what additional lines to capture. Do not recommend simply increasing retries to hide failures without a tracking ticket. Do not invent tool-specific settings; mark any CI configuration advice [VERIFY] for [CI_TOOL] and our version. Do not suggest disabling tests without a named owner and a review date.

Fill in before use

Optional: type your details and the prompt above updates. Nothing is saved or sent.

Replace each bracketed placeholder with your own details, then paste into Any AI or another assistant.