DEVOPS
Agent-driven root-cause triage of newly quarantined tests
When a test is freshly quarantined, an agent pulls recent failure logs and the test source, reasons about the likely cause (timing, ordering, shared state, network), and writes…
How it runs
The automated pipeline, trigger to output.
- TriggerWebhook: test added to quarantine manifestHTTP webhook
- ActionFetch test source and failure logsGitHub
- ActionQuery Datadog for failure timing and concurrencyDatadog
- LogicAgent classifies flake cause and drafts fix plan
- ActionWrite triage report into Linear issueLinear
- OutputAssign issue to owning team via CODEOWNERSGitHub
What it does
Turns a raw quarantine event into an actionable diagnosis. An agent gathers the failing test's source, its recent failure logs, and the surrounding test fixtures, then reasons about the most probable flake category and proposes a concrete remediation direction. The findings are written back into the tracking issue so the assignee starts with a hypothesis, not a blank page.
When to use it
Use this when quarantined tests pile up faster than engineers can investigate them. It front-loads the tedious log-reading and pattern-matching so triage time drops from hours to minutes.
How it works
- 1A webhook fires when a test is added to the quarantine manifest.
- 2The agent fetches the test source and recent failure logs from GitHub.
- 3It queries Datadog for the test's historical failure timing and concurrency context.
- 4The agent classifies the likely cause (race condition, test ordering, shared fixture, external dependency) and drafts a remediation plan.
- 5It writes the structured triage report and suggested fix class into the Linear issue.
- 6The final step assigns the issue to the owning team based on CODEOWNERS.
Set it up
What you configure once, before turning it on.
- 1Connect GitHubRepos, issues, pull requests, actions.
- 2Connect DatadogMetrics, traces, log search.
- 3Connect LinearIssues, projects, cycles, triage.
- 4Connect HTTP webhookTrigger any URL on agent actions.
- 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 DevOps workflows
Block costly Hugging Face Space hardware upgrades in PR review
When a pull request changes a Space's hardware config, it estimates the new monthly cost and posts a GitHub PR comment that flags upgrades crossing a budget ceiling.
Auto-spin a Zoom war-room when PagerDuty hits SEV-1
When a PagerDuty incident escalates to a critical severity, this workflow creates a dedicated Zoom meeting and posts the bridge link to the incident's Slack channel so responders…
Page on-call when a Hugging Face Space build is stuck or errored
Polls Hugging Face Space runtime status on a schedule and opens a PagerDuty incident when a Space sits in a build or error state past a deadline, with a Slack heads-up.
Slack-approved pause for idle Hugging Face Spaces
On a daily scan it finds idle paid Spaces and posts an interactive Slack approval; on approve it pauses the Space and logs the decision to a GitHub issue audit trail.
Hugging Face Spaces idle-runtime sweep with auto-pause
On a schedule, scans all Hugging Face Spaces for ones running idle past a threshold, pauses them to stop billing, and posts a Slack summary with the estimated monthly savings.
Open a Zoom war-room from a Datadog multi-alert storm
When a Datadog monitor crosses a critical threshold, this workflow dedupes against active incidents, and only for a genuinely new outage it creates a Zoom bridge.
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.