ENGINEERING
Flake Evidence Collector: Auto-Rerun a Suspect Test N Times to Confirm Flakiness
On a single test failure, dispatches the same test in isolation several times to measure its real failure rate.
How it runs
The automated pipeline, trigger to output.
- TriggerGitHub webhook: single test failureGitHub
- ActionDispatch N isolated reruns of the testGitHub
- LogicTally rerun pass/fail ratio; classify hard-fail vs. flaky
- ActionSummarize flakiness with rerun evidenceOpenAI
- OutputOpen Linear flake ticket + draft skip MR with evidenceLinear
What it does
A single red run proves nothing. This agent reruns the suspect test in isolation multiple times, records the pass/fail pattern, and uses that evidence to decide. A test that fails every rerun is a hard failure and is escalated; one that fails some-but-not-all reruns is confirmed flaky and quarantined with the evidence attached.
When to use it
Use it when you want proof before quarantining, and when your CI lets you dispatch a targeted test run on demand. It eliminates guesswork by generating a real flakiness sample instead of inferring from one failure.
How it works
- 1A GitHub webhook fires on a single test failure.
- 2The flow dispatches N isolated reruns of just that test via the GitHub API and waits for results.
- 3A logic step tallies the pass/fail ratio across the reruns.
- 4If the test failed every time, it opens a GitHub regression issue and stops.
- 5If it failed intermittently, an OpenAI step writes a flake summary with the rerun evidence.
- 6It opens a Linear flake ticket and a draft skip MR, attaching the rerun pass/fail record.
Set it up
What you configure once, before turning it on.
- 1Connect GitHubRepos, issues, pull requests, actions.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect LinearIssues, projects, cycles, triage.
- 4Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 5Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 6Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Engineering workflows
Gate breaking API PRs behind downstream consumer acknowledgement
When a PR introduces a breaking contract change, comments the impact summary back on the PR, applies a blocking label.
Publish a versioned API changelog to Confluence on each release tag
On a new semver release tag, gathers the contract changes since the last release and writes a clean.
Agent reviews model-license fit and suggests compliant swaps on the PR
When a PR adds a Hugging Face model, an agent reads the model card and license, judges fit against your commercial-use policy.
Upgrade Impact Router to Module Code Owners
Maps a dependency-bump PR's affected modules to their CODEOWNERS, then DMs each owner on Slack with only the changelog slice that touches code they own.
Re-Voice IVR Prompts on Phone-Tree Config Merge
When a phone-tree config change merges in GitHub, regenerates the ElevenLabs audio for any prompt whose script changed in the diff and opens a follow-up PR adding the new audio…
Upstream Release to Notion Upgrade Brief
When a watched package publishes a new release, fetches the release notes, maps them to the internal modules that depend on it.
Run it inside a business
This workflow drops into a full company template. Import the org, and this is one of the playbooks its agents run.
Run this workflow in your colony.
14-day trial. No DevOps. No Sales call. Provisioned in under a minute.