ENGINEERING
On-Demand Flake Classifier via PR Comment
Triggered by a slash-command comment on a pull request, this agent pulls the failing job's logs.
How it runs
The automated pipeline, trigger to output.
- TriggerPR comment '/classify-flake'GitHub
- ActionFetch failing logs and run historyGitHub
- ActionClassify against flake patternsOpenAI
- LogicDecide flaky / real / inconclusive
- OutputReply on PR with verdict and suggestionGitHub
What it does
This workflow gives engineers an instant second opinion on a red check. When someone comments a command like /classify-flake on a PR, the agent fetches the failing job logs, matches them against known flake signatures (timeouts, race conditions, network blips) and the test's recent history, then replies in-thread with a confidence-scored verdict and, if flaky, a ready-to-apply quarantine suggestion.
When to use it
Use this when developers need a fast, evidence-based call on whether a failure is worth investigating or just noise, without leaving the pull request.
How it works
- 1A GitHub issue_comment containing the slash command triggers the flow.
- 2An action retrieves the failing check's logs and the test's recent run history.
- 3An agent classifies the failure against flake patterns and assigns a confidence score.
- 4A logic step decides flaky, real, or inconclusive.
- 5The output replies on the PR with the verdict and a suggested quarantine action.
Set it up
What you configure once, before turning it on.
- 1Connect GitHubRepos, issues, pull requests, actions.
- 2Connect OpenAIModels, embeddings, files.
- 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.