ENGINEERING
Flaky Test Triage Agent with Owner Routing
An agent investigates each newly quarantined flaky test, reads the failing logs and CODEOWNERS to identify the likely cause and owner.
How it runs
The automated pipeline, trigger to output.
- TriggerGitHub issue labeled flaky-test openedGitHub
- ActionFetch CI logs and test sourceGitHub
- LogicDiagnose cause and resolve owner from CODEOWNERS
- ActionComment root-cause summary on issueGitHub
- OutputNotify owner in SlackSlack
What it does
This agent-driven workflow does the human-like triage on a freshly quarantined flaky test. It reads the failing run logs, inspects the test file and surrounding code, consults CODEOWNERS to find the responsible team, and writes a plain-language root-cause hypothesis (timing, shared state, network, ordering) into the GitHub tracking issue. It then notifies the owner in Slack with a concise summary and the issue link.
When to use it
Use this when flaky tests pile up faster than engineers can investigate them and you want a first-pass diagnosis and clear ownership before anyone opens the logs.
How it works
- 1A GitHub issue labeled `flaky-test` is opened, triggering the agent.
- 2The agent fetches the linked CI logs and the test source from the repository.
- 3It reasons over the evidence to classify the likely flakiness cause and resolves the owning team from CODEOWNERS.
- 4It posts a structured root-cause comment and suggested next step onto the tracking issue.
- 5It sends the owner a Slack message with the diagnosis and a direct link to act on.
Set it up
What you configure once, before turning it on.
- 1Connect GitHubRepos, issues, pull requests, actions.
- 2Connect SlackChannels, DMs, threads, mentions.
- 3Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 4Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 5Test, 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.