AI & RAG
Detect Breaking API Changes from Spec Diffs and Alert Owners
Compares the new OpenAPI spec against the previous version on each GitLab merge, uses retrieval over the changelog to classify whether changes are breaking.
How it runs
The automated pipeline, trigger to output.
- TriggerGitLab merge touches an OpenAPI specGitLab
- ActionFetch prior and new spec versions and diff themGitLab
- ActionClassify deltas as breaking using changelog retrievalOpenAI
- LogicBranch on whether breaking changes exist
- OutputAlert endpoint owners in Slack with summarySlack
What it does
When a spec changes in GitLab, this pipeline diffs the new OpenAPI document against the prior version, identifies removed or altered operations and required fields, cross-references the changelog via retrieval to confirm intent, and classifies each change as breaking or safe. If anything is breaking, it sends a targeted alert with an explanation.
When to use it
Use it to catch accidental breaking changes before consumers do. Ideal for platform teams publishing APIs to many internal clients who need early, specific warnings rather than a wall of diff noise.
How it works
- 1A GitLab merge touching the spec triggers the flow.
- 2The previous and new spec versions are fetched and structurally diffed.
- 3Retrieval over the changelog grounds an OpenAI call that classifies each delta as breaking or safe.
- 4A branch checks whether any breaking changes were found.
- 5If breaking, a summary with affected endpoints is sent to the owners' Slack channel; if safe, the run ends quietly.
Set it up
What you configure once, before turning it on.
- 1Connect GitLabRepos, MRs, pipelines, registry.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect SlackChannels, DMs, threads, mentions.
- 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 AI & RAG workflows
RFP and security questionnaire drafter grounded in Coda
Drafts answers to inbound RFP and security questionnaire questions by retrieving approved language from your Coda hub, then files the cited draft for review before a rep sends it.
Grounded reply suggestions for inbound sales email
Reads inbound prospect emails, retrieves the matching answers from your Coda hub.
Coda-grounded sales answer bot with citations in Slack
Reps ask product, pricing, or competitive questions in Slack and get an answer drawn only from your Coda knowledge hub, with links to the exact docs and rows it pulled from.
On-Call Spec Answerer from Dropbox Engineering Corpus
Answers on-call questions posted in a Slack channel by retrieving the most relevant Dropbox engineering specs and replying with a grounded, source-cited answer in the thread.
Agentic Deep-Dive API Researcher for Hard Spec Questions
An agent fielded via webhook that answers multi-part API questions by iteratively searching OpenAPI specs, changelogs, and Confluence runbooks.
Publish a Grounded API FAQ Page to Confluence Weekly
Each week, clusters the top unanswered or repeated API questions, generates spec-grounded answers with citations.
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.