ENGINEERING
Suggest the best GitLab MR reviewer with an agent
On MR open, an agent weighs code ownership, recent file expertise, current queue depth, and availability to recommend the strongest reviewer.
How it runs
The automated pipeline, trigger to output.
- TriggerGitLab MR openedGitLab
- ActionGather diff, owners, recent file authorsGitLab
- ActionRead candidate queue depth and availabilityPostgres
- LogicAgent ranks candidates by expertise and loadOpenAI
- OutputPost suggestion with rationale to Slack to confirmSlack
What it does
This workflow uses an agent to make a judgment call the rule-based balancer can't. For a new merge request it gathers the code owners, who has recently touched the changed files, each candidate's live queue depth, and their availability, then reasons over those signals to recommend the reviewer who best balances fairness against domain expertise. It posts the recommendation with a short rationale to Slack for the team to confirm.
When to use it
Use it when pure round-robin load balancing assigns reviews to people who don't know the affected code. The agent keeps load even while still favoring the right expertise for tricky changes.
How it works
- 1A GitLab webhook fires on MR open.
- 2The workflow pulls the diff, CODEOWNERS matches, and recent commit authors for the changed files.
- 3It reads each candidate's current queue depth and availability from Postgres.
- 4The agent weighs ownership, recency of expertise, load, and availability to rank candidates and explain its top pick.
- 5It posts the ranked suggestion and rationale to Slack with a confirm action.
- 6On confirm, it assigns the reviewer in GitLab and records the choice.
Set it up
What you configure once, before turning it on.
- 1Connect GitLabRepos, MRs, pipelines, registry.
- 2Connect PostgresAny Postgres URL — query, write, migrate.
- 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.