ENGINEERING
Enrich a thin GitLab MR description with an AI summary
When an MR has a short or empty description, it generates a structured summary from the diff and commit messages, then writes it into the MR description with an edit-safe marker.
How it runs
The automated pipeline, trigger to output.
- TriggerGitLab MR opened or updated webhookGitLab
- LogicSkip if description is already adequate
- ActionFetch diff and commit messagesGitLab
- ActionGenerate structured summaryOpenAI
- OutputWrite summary into MR descriptionGitLab
What it does
This workflow fills in the blanks on lazily described merge requests. It detects MRs whose description is empty or below a length threshold, feeds the diff and commit messages to an LLM, and writes back a structured summary covering what changed, why, and what reviewers should look at. The generated section is wrapped in a marker so the author's own text is never overwritten.
When to use it
Use it on teams where MR descriptions are routinely one-liners, slowing review and polluting the changelog. It raises the floor on description quality without forcing authors to fill a template by hand.
How it works
- 1A GitLab MR opened/updated webhook fires.
- 2A logic step checks whether the description is missing or shorter than the threshold; if it is adequate, the run stops.
- 3The workflow fetches the diff and commit messages for the MR.
- 4An OpenAI step generates a structured summary (changes, rationale, review focus).
- 5It updates the MR description, inserting the summary inside a managed marker block while preserving any existing author text.
Set it up
What you configure once, before turning it on.
- 1Connect GitLabRepos, MRs, pipelines, registry.
- 2Connect OpenAIModels, embeddings, files.
- 3Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 4Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 5Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Engineering workflows
Upgrade Impact Router to Module Code Owners
Maps a dependency-bump PR's affected modules to their CODEOWNERS, then DMs each owner on Slack with only the changelog slice that touches code they own.
Re-Voice IVR Prompts on Phone-Tree Config Merge
When a phone-tree config change merges in GitHub, regenerates the ElevenLabs audio for any prompt whose script changed in the diff and opens a follow-up PR adding the new audio…
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.
Scan for deprecated endpoints and email consumers a weekly sunset countdown
On a weekly schedule, scans the OpenAPI spec for endpoints marked deprecated with a sunset date, and emails each consuming team a countdown of how many days remain before removal.
Publish a versioned API changelog to Confluence on each release tag
On a new semver release tag, gathers the contract changes since the last release and writes a clean.
Gate breaking API PRs behind downstream consumer acknowledgement
When a PR introduces a breaking contract change, comments the impact summary back on the PR, applies a blocking label.
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.