ENGINEERING
Locate deprecated calls in GitLab and draft a migration MR
When a high-volume deprecation appears in Sentry, searches the GitLab repo for every call site, uses OpenAI to draft the replacement edits.
How it runs
The automated pipeline, trigger to output.
- TriggerHigh-volume deprecation in SentrySentry
- ActionSearch GitLab repo for deprecated call sitesGitLab
- LogicBranch on call-site count and ambiguity
- ActionDraft replacement edits with OpenAIOpenAI
- OutputOpen draft merge request in GitLabGitLab
What it does
For a deprecation that fires often enough to matter, this workflow finds where the deprecated API is actually called across your GitLab repository, drafts the mechanical replacement edits with OpenAI, and opens a draft merge request. An engineer reviews and finishes the work instead of starting from a blank diff.
When to use it
Use it for mechanical, repetitive deprecations (a renamed function, a changed argument, a moved import) where the bottleneck is finding all the call sites and writing boilerplate edits. Not for risky semantic migrations that need human design.
How it works
- 1Sentry fires when a deprecation crosses an event-volume threshold.
- 2The flow searches the GitLab repo for the deprecated symbol and gathers each matching file and line.
- 3A branch decides whether the count is small enough to auto-draft; large or ambiguous matches stop for manual review.
- 4OpenAI generates the replacement edits per file plus a migration summary.
- 5It opens a draft merge request on a new branch with the edits, the summary, and a link back to the Sentry issue.
Set it up
What you configure once, before turning it on.
- 1Connect SentryErrors, performance, releases.
- 2Connect GitLabRepos, MRs, pipelines, registry.
- 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.