ENGINEERING
Triage and draft a budget-recovery plan when an SLO freeze trips
When a deploy freeze is triggered by budget exhaustion, an agent investigates recent deploys and error patterns, drafts a recovery plan, files a Linear incident issue.
How it runs
The automated pipeline, trigger to output.
- TriggerFreeze-triggered webhook firesHTTP webhook
- ActionGather recent GitLab deploys + budget timelineGitLab
- LogicAgent reasons about likely cause + recovery path
- ActionFile Linear incident issue with recovery planLinear
- OutputPost plan to Slack for on-call approvalSlack
What it does
This workflow adds an investigative agent on top of the freeze gate. When a budget-exhaustion freeze fires, the agent pulls the recent deploy history and error-budget context, reasons about the most likely cause, and drafts a concrete recovery plan (rollback candidate, suspect change, mitigation steps). It files a Linear incident issue with that plan attached and posts a summary to Slack for the on-call engineer to approve or edit.
When to use it
Use this when a raw freeze alert is not enough and you want a first-draft incident writeup and remediation plan ready the moment the gate trips, cutting the time the on-call spends gathering context.
How it works
- 1A freeze-triggered webhook fires with the service and burn details.
- 2The agent gathers recent GitLab deploys and the error-budget timeline for the service.
- 3It reasons over the data to identify the likely culprit and a recovery path.
- 4It creates a Linear incident issue containing the drafted recovery plan.
- 5It posts the plan summary to Slack and asks the on-call to approve.
Set it up
What you configure once, before turning it on.
- 1Connect HTTP webhookTrigger any URL on agent actions.
- 2Connect GitLabRepos, MRs, pipelines, registry.
- 3Connect LinearIssues, projects, cycles, triage.
- 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.