ENGINEERING
Triage new Sentry security issues into a GitLab review-ready issue
When Sentry flags a new high-severity error tagged as security, this drafts a triaged summary with OpenAI, opens a labeled GitLab issue assigned to the security reviewer group.
How it runs
The automated pipeline, trigger to output.
- TriggerSentry alert: new high-severity security issueSentry
- ActionFetch full issue detail and events from SentrySentry
- ActionDraft a triage summary with OpenAIOpenAI
- ActionOpen a labeled GitLab issue for the reviewer groupGitLab
- OutputNotify the security team in SlackSlack
What it does
Reacts to new high-severity Sentry issues that carry a security tag. It pulls the stack trace and event context, uses OpenAI to write a concise triage summary with a likely-affected-area guess and severity rationale, then opens a GitLab issue pre-labeled `security` and assigned to the reviewer group — so the fix MR lands with an owner already attached.
When to use it
Use it when security-relevant production errors need to become tracked, owned work fast, and you want the triage write-up and routing done automatically instead of an engineer copy-pasting Sentry into a ticket at 2am.
How it works
- 1A Sentry alert fires on a new high-severity, security-tagged issue.
- 2The flow fetches the full issue detail and recent events from Sentry.
- 3OpenAI produces a triage summary: probable cause, affected area, and severity.
- 4The flow opens a GitLab issue with the `security` label and assigns the reviewer group.
- 5A Slack message notifies the team with the issue link and the triage summary.
Set it up
What you configure once, before turning it on.
- 1Connect SentryErrors, performance, releases.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect GitLabRepos, MRs, pipelines, registry.
- 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.