ENGINEERING
Classify and Quarantine Intermittent CI Failures with AI
When a CI job fails, an agent reads the failure logs to decide whether it is a real regression or flakiness.
How it runs
The automated pipeline, trigger to output.
- TriggerGitHub failed workflow runGitHub
- ActionFetch test logs and recent historyGitHub
- LogicAgent classifies: regression vs. flaky
- ActionOpen labeled quarantine issue (if flaky)GitHub
- ActionPage on-call (if real regression)PagerDuty
- OutputPost classification reasoning to SlackSlack
What it does
On every failed CI run, an agent inspects the failure logs and the test's recent history to classify the failure as either a real regression or intermittent flakiness. Confirmed flakes are quarantined (labeled GitHub issue + skip entry); suspected real breakages are escalated to on-call so they aren't silently hidden.
When to use it
Use it when naive auto-quarantine is too risky — you don't want to hide a genuine regression behind a flaky label. The agent adds judgment by reading stack traces, timeout patterns, and prior pass/fail history before deciding.
How it works
- 1A GitHub webhook fires on a failed workflow run.
- 2The agent fetches the failing test's logs and its recent pass/fail history via the GitHub API.
- 3It classifies the failure: real regression vs. flaky (timeouts, ordering, network jitter, race conditions).
- 4If flaky, it opens a labeled quarantine issue and records the rationale.
- 5If a likely real regression, it pages on-call via PagerDuty with the diagnosis.
- 6It posts the classification and reasoning to Slack for visibility.
Set it up
What you configure once, before turning it on.
- 1Connect GitHubRepos, issues, pull requests, actions.
- 2Connect PagerDutyIncidents, on-call, escalations.
- 3Connect SlackChannels, DMs, threads, mentions.
- 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
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…
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.
Scan for deprecated endpoints and email consumers a weekly sunset countdown
On a weekly schedule, scans the OpenAPI spec for endpoints marked deprecated with a sunset date, and emails each consuming team a countdown of how many days remain before removal.
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.
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.
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.