ENGINEERING
Explain a flagged coverage drop when a reviewer asks
When a reviewer comments a trigger phrase on an MR, it analyzes which changed files dropped coverage and replies with a plain-English, file-level explanation and suggested tests.
How it runs
The automated pipeline, trigger to output.
- TriggerGitLab MR comment matches trigger phraseGitLab
- ActionFetch coverage report and changed filesGitLab
- ActionIsolate files and lines that lost coverageShell
- ActionExplain drop and suggest testsOpenAI
- OutputPost explanation as MR reply noteGitLab
What it does
This workflow answers the natural follow-up to a coverage-delta note: why did it drop. When a reviewer posts a trigger phrase (for example, `/why-coverage`) in an MR comment, it pulls the coverage diff for that MR, identifies the specific files and lines that lost coverage, and asks an LLM to explain in plain English what is now untested and which tests would close the gap. The answer is posted as a reply note on the MR.
When to use it
Use it when the raw coverage-delta number isn't actionable on its own and reviewers keep asking authors to chase down the cause by hand. This turns the question into a one-line command.
How it works
- 1A GitLab note (comment) webhook fires and matches the trigger phrase.
- 2The workflow fetches the MR's coverage report and changed files.
- 3A shell step isolates the files and lines whose coverage decreased.
- 4An OpenAI step turns that into a readable explanation plus concrete test suggestions.
- 5It posts the explanation as a threaded reply note on the merge request.
Set it up
What you configure once, before turning it on.
- 1Connect GitLabRepos, MRs, pipelines, registry.
- 2Connect ShellRun sandboxed commands inside the workspace.
- 3Connect OpenAIModels, embeddings, files.
- 4Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 5Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 6Test, 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.