ENGINEERING
Agent Triage of a Quarantined Test with Root-Cause Notes
When a test is newly quarantined, an agent pulls recent failure logs from Datadog and the test source from GitHub, drafts a likely-root-cause analysis.
How it runs
The automated pipeline, trigger to output.
- TriggerLinear issue labeled flaky-quarantine webhookLinear
- ActionFetch failure traces from Datadog CI VisibilityDatadog
- ActionRead test source and git blame from GitHubGitHub
- LogicAgent reasons over evidence to draft root-cause hypothesis
- ActionPost analysis and set deadline on Linear issueLinear
- OutputNotify owner in Slack that triage is readySlack
What it does
Adds an investigative layer on top of quarantine. Whenever a test gets quarantined, an agent gathers the evidence and produces a first-pass root-cause hypothesis so the owner opens the ticket already pointed at the likely culprit.
When to use it
Use this when quarantine tickets land on owners with no context and the fix stalls because nobody has time to dig. The agent does the initial digging and frees the owner to validate rather than start cold.
How it works
- 1A webhook fires when a Linear issue is labeled 'flaky-quarantine'.
- 2The agent fetches recent failure traces and error patterns for that test from Datadog CI Visibility.
- 3It reads the test file and recent git blame on it from GitHub to spot timing, ordering, or shared-state risks.
- 4The agent reasons over the evidence and drafts a root-cause hypothesis with concrete next steps and suspect lines.
- 5It posts the analysis as a comment on the Linear issue and sets a re-enable deadline based on assessed difficulty.
- 6The owner is notified in Slack that triage notes are ready.
Set it up
What you configure once, before turning it on.
- 1Connect LinearIssues, projects, cycles, triage.
- 2Connect DatadogMetrics, traces, log search.
- 3Connect GitHubRepos, issues, pull requests, actions.
- 4Connect SlackChannels, DMs, threads, mentions.
- 5Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 6Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 7Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Engineering workflows
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.
Block PRs that add incompatible Hugging Face model licenses
When a pull request adds or bumps a Hugging Face model dependency, it fetches the model card license, checks it against your org's allowed-license policy.
Quarterly Logging Hygiene Audit Agent
An agent-driven quarterly sweep that surveys all Axiom datasets, builds a logging-hygiene scorecard per service.
Post-Merge Log Volume Recheck After Downsampling PR
After a log-level PR merges, waits a day then re-queries Axiom to confirm the targeted stream's volume actually dropped.
Axiom Ingest Cost Spike to Linear Triage Ticket
When Axiom ingest volume spikes beyond its baseline, identifies which service caused it and files a Linear ticket with the offending log stream, sample lines, and a downsampling…
File a Linear license-review ticket for risky model adds
When a PR introduces a Hugging Face model with a non-permissive or unknown license, it opens a Linear issue assigned to the legal-review team with the model, license.
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.