AI & RAG
PR Reviewer That Flags Decisions Against ADRs
On every pull request, retrieves the ADRs touching the changed areas and posts a review comment when the diff appears to contradict an accepted decision.
How it runs
The automated pipeline, trigger to output.
- TriggerPull request opened or updatedGitHub
- ActionFetch changed files and diffGitHub
- ActionRetrieve ADRs governing the touched areasConfluence
- ActionDetect diff vs accepted-ADR conflictsOpenAI
- LogicSkip when no accepted ADR is implicated
- OutputPost citing review comment on the PRGitHub
What it does
Guards your architecture at review time. When a pull request opens, it figures out which Architecture Decision Records govern the changed files, then checks whether the diff conflicts with any accepted decision. If it finds a likely violation, it leaves a PR comment quoting the relevant ADR and explaining the conflict so the author can fix it or amend the decision.
When to use it
When accepted ADRs keep getting silently broken — a banned dependency creeps back, a deprecated pattern returns, a data-residency rule is ignored. Best for teams that want enforcement without a human gatekeeper reading every diff.
How it works
- 1A pull request is opened or updated in GitHub.
- 2The changed file paths and diff are pulled for analysis.
- 3Matching ADRs are retrieved from the GitHub docs folder or Confluence, scoped to the touched areas.
- 4OpenAI compares the diff against each accepted ADR and decides whether a real conflict exists.
- 5A logic step suppresses comments when no accepted ADR is implicated.
- 6If a conflict is found, a review comment is posted citing the ADR number and the contradicting lines.
Set it up
What you configure once, before turning it on.
- 1Connect GitHubRepos, issues, pull requests, actions.
- 2Connect ConfluenceSpaces, pages, blueprints.
- 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 AI & RAG workflows
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.
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.
Pre-meeting prep brief grounded in Coda and CRM
Before each booked sales meeting, builds a one-page prep brief by combining the account's HubSpot context with grounded talking points and objection responses pulled from your…
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.
Weekly knowledge-gap digest from unanswered rep questions
Each week, scans rep questions the answer bot couldn't ground in Coda, clusters the recurring gaps.
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.
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.