ENGINEERING
Blocked-promotion triage and postmortem drafter
When a promotion gate blocks a release, an agent pulls the failing Sentry issues, correlates them to the GitHub commits in the release.
How it runs
The automated pipeline, trigger to output.
- TriggerGate-blocked-promotion webhook
- ActionFetch top unresolved Sentry issues for releaseSentry
- ActionPull GitHub commit range + authorsGitHub
- LogicCorrelate stack frames to suspect commits
- ActionFile Linear ticket to likely ownerLinear
- ActionDraft Confluence postmortem stubConfluence
- OutputLink artifacts back into SlackSlack
What it does
Turns a blocked promotion into a head start on the fix. Triggered when the gate vetoes a release, the agent gathers the top crash-driving Sentry issues, maps each to the commits and authors introduced in that release via GitHub, reasons about the most likely regression source, and produces written artifacts the team can act on.
When to use it
Use it downstream of any of the gating workflows so a failed promotion does not just sit as a Slack message. Best when you want the investigation kickoff — suspect commits, owner, and a draft writeup — ready before an engineer opens their laptop.
How it works
- 1A webhook fires when a promotion gate records a block decision, carrying the release tag.
- 2The agent queries Sentry for the release's top unresolved issues by event volume.
- 3It pulls the GitHub commit range and authors for that release.
- 4It correlates failing issue stack frames to changed files to nominate suspect commits.
- 5It files a Linear ticket assigned to the likely owner with the evidence attached.
- 6It drafts a Confluence postmortem stub and links everything back into Slack.
Set it up
What you configure once, before turning it on.
- 1Connect SentryErrors, performance, releases.
- 2Connect GitHubRepos, issues, pull requests, actions.
- 3Connect LinearIssues, projects, cycles, triage.
- 4Connect ConfluenceSpaces, pages, blueprints.
- 5Connect SlackChannels, DMs, threads, mentions.
- 6Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 7Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 8Test, 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.