ENGINEERING
AI triage agent: Sentry spike to GitHub issue with suspect commit
An agent investigates a spiking Sentry issue, reads the stack trace and recent commits to the affected files, names the most likely suspect commit and owner.
How it runs
The automated pipeline, trigger to output.
- TriggerSentry spike webhook delivers issue and stack traceSentry
- ActionQuery GitHub for recent commits to affected filesGitHub
- ActionLLM ranks suspect commit and drafts root-cause hypothesisOpenAI
- ActionCreate GitHub issue assigned to suspect author with linksGitHub
- OutputPost agent's finding to the team Slack channelSlack
What it does
Goes beyond filing a ticket: an agent reasons over the stack trace and recent Git history to propose which commit likely caused the spike, who owns it, and what to check first, then files an assigned GitHub issue with that hypothesis.
When to use it
Use it when raw error alerts cost your team triage time and you want a first-pass investigation done before a human looks. Best for repos with clear file ownership and frequent deploys where blame-by-commit is meaningful.
How it works
- 1Sentry's spike alert webhook delivers the issue, stack trace, and affected release.
- 2The agent pulls the frames from the trace and queries GitHub for recent commits touching those files since the last good release.
- 3It correlates timing and changed lines to rank the most likely suspect commit and its author.
- 4An LLM step drafts a concise hypothesis: probable cause, suspect commit, and suggested first check.
- 5A GitHub issue is created, assigned to the suspect author, labeled by severity, and linked to both the Sentry issue and the suspect commit.
- 6A Slack note goes to the team channel summarizing the agent's finding.
Set it up
What you configure once, before turning it on.
- 1Connect SentryErrors, performance, releases.
- 2Connect GitHubRepos, issues, pull requests, actions.
- 3Connect OpenAIModels, embeddings, files.
- 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.