DEVOPS
Agent-Driven Stale Environment Triage to Linear
An agent reviews stale preview and staging environments across GitHub and Vercel, reasons about which are safe to reap versus needs-owner-input, asks ambiguous owners in Slack.
How it runs
The automated pipeline, trigger to output.
- TriggerWeekly schedule fires
- ActionAgent gathers Vercel + GitHub env stateVercel
- LogicAgent classifies reap / ask / keep
- ActionReap clear cases via VercelVercel
- ActionAsk owners in Slack for ambiguous onesSlack
- ActionFile Linear issues for leftoversLinear
- OutputPost triage summary to SlackSlack
What it does
Deploys an agent to triage the long tail of stale environments that simple age rules get wrong. It correlates each environment with its branch, last commit, open-PR status, and recent activity, then classifies it as safe-to-reap, needs-owner-decision, or keep — reaping the clear cases and routing the rest to humans.
When to use it
Use when naive TTL deletion is too risky because some old previews back demos, audits, or long-running branches. The agent's judgment handles edge cases a deterministic filter would mis-delete.
How it works
- 1A weekly schedule starts the triage run.
- 2The agent gathers candidate environments from Vercel and cross-references branch and PR state in GitHub.
- 3It reasons per environment, classifying each as reap, ask, or keep with a rationale.
- 4For reap cases, it deletes the Vercel deployment directly.
- 5For ask cases, it DMs the owner in Slack to confirm before any action.
- 6For unresolved or risky cases, it files a Linear issue with context and a recommendation, then posts a triage summary to Slack.
Set it up
What you configure once, before turning it on.
- 1Connect VercelDeploys, runtime logs, analytics.
- 2Connect GitHubRepos, issues, pull requests, actions.
- 3Connect SlackChannels, DMs, threads, mentions.
- 4Connect LinearIssues, projects, cycles, triage.
- 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.