DEVOPS
Triage a failed preview smoke gate with an AI root-cause agent
When a preview smoke gate fails, an agent pulls the build logs and failing responses, diagnoses the likely cause, files a Linear issue, and comments the analysis on the PR.
How it runs
The automated pipeline, trigger to output.
- TriggerPreview smoke gate failed
- ActionFetch Vercel build and function logsVercel
- ActionAgent diagnoses likely root causeOpenAI
- ActionFile Linear issue with evidenceLinear
- OutputComment root-cause analysis on PRGitHub
What it does
Replaces the manual scramble after a red preview gate. When smoke checks fail, an agent gathers the Vercel build and runtime logs plus the failing HTTP responses, reasons about the most probable root cause (bad env var, broken route, failed migration, upstream timeout), and writes a plain-language diagnosis. It then files a Linear issue with the evidence and drops the same summary as a PR comment so the author starts debugging with a hypothesis already in hand.
When to use it
Use it when preview failures are common enough that triage eats real engineering time, and the first ten minutes are always the same log-spelunking. Best for teams that want failures captured as tracked work rather than lost in a CI log.
How it works
- 1A preview smoke gate failure event starts the run.
- 2A Vercel action fetches the deployment's build and function logs.
- 3The agent correlates logs with the failing endpoints and drafts a root-cause hypothesis.
- 4A Linear action files an issue with the diagnosis, preview URL, and log excerpts.
- 5A GitHub action posts the same analysis as a comment on the PR.
Set it up
What you configure once, before turning it on.
- 1Connect VercelDeploys, runtime logs, analytics.
- 2Connect LinearIssues, projects, cycles, triage.
- 3Connect GitHubRepos, issues, pull requests, actions.
- 4Connect OpenAIModels, embeddings, files.
- 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
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.
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.
Generate a weekly de-flake report and assign Linear cleanup tickets
On a weekly schedule, aggregates the current quarantine manifest and recent flake history, builds a prioritized report.
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-release tests from quarantine once they prove stable
Triggered by a webhook from a nightly stability runner, checks whether quarantined tests have passed enough consecutive runs, removes the stable ones from quarantine in GitHub.
Quarantine a test on demand from a PR comment command
Triggered when an engineer comments a quarantine command on a pull request, validates the test name, commits the quarantine change to that PR branch, opens a tracking issue.
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.