AI AGENTS
Sentry Release-Health Crash to PagerDuty + Repro MR
When a new release's crash-free rate drops below target, an agent reproduces the top new crash, opens a GitLab MR with a failing test.
How it runs
The automated pipeline, trigger to output.
- TriggerSentry release crash-free rate drops below targetSentry
- ActionIdentify top new crash for the releaseSentry
- ActionReproduce and write failing test in shellShell
- ActionOpen GitLab MR linking release and issueGitLab
- LogicPage only if reproduced and above severity floor
- OutputTrigger PagerDuty incident with MR attachedPagerDuty
What it does
Ties release health to on-call escalation. When Sentry reports a release's crash-free session rate falling below your threshold, the agent identifies the top new crash introduced by that release, reproduces it, writes a failing test, opens a GitLab MR, and pages on-call through PagerDuty with the MR and repro attached so the responder has a confirmed defect, not just a metric.
When to use it
Use it during active rollouts when a crash-free regression must wake someone, but you want them to receive a reproduced, test-backed bug instead of a bare alert.
How it works
- 1A Sentry release-health alert fires on a crash-free rate drop.
- 2The agent identifies the top new crash attributed to the failing release.
- 3It reproduces the crash in a shell sandbox and writes a failing test.
- 4The agent opens a GitLab MR linking the release and Sentry issue.
- 5Logic gate: page only if the crash reproduces and exceeds the severity floor.
- 6It triggers a PagerDuty incident with the MR link and repro summary attached.
Set it up
What you configure once, before turning it on.
- 1Connect SentryErrors, performance, releases.
- 2Connect ShellRun sandboxed commands inside the workspace.
- 3Connect GitLabRepos, MRs, pipelines, registry.
- 4Connect PagerDutyIncidents, on-call, escalations.
- 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 AI Agents workflows
Custom Metrics Cardinality Spike Pager
A webhook from a Datadog monitor fires when custom-metric cardinality jumps; an agent pinpoints the offending metric and tag, estimates the added cost.
Sentry-to-Confluence Runbook Updater
When a Sentry issue is resolved, the agent finds the matching Confluence runbook page and proposes an inline update with the verified fix.
Stale Doc-PR Chaser for Runbook Gaps
On a daily schedule the agent finds runbook doc PRs that were opened from resolved incidents but never reviewed, summarizes what each one fixes.
Resolved Incident to Public Troubleshooting Doc
For customer-facing errors resolved in Sentry, the agent drafts a sanitized troubleshooting entry and opens a PR to your ReadMe documentation.
On-Call Runbook Gap Closer: Resolved Sentry Issues to Doc PRs
An agent reads each newly resolved Sentry issue, compares the actual fix against your existing runbook, and opens a GitHub PR adding the missing remediation steps.
Weekly On-Call Doc-Gap Digest
Each week the agent reviews every Sentry issue resolved in the last 7 days, ranks the ones whose runbook coverage is missing or thin.
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.