AI & RAG
ADR Conflict Check: flag PRs that contradict accepted decisions
When a pull request opens, retrieves relevant accepted ADRs and uses an LLM to judge whether the change conflicts with a standing decision.
How it runs
The automated pipeline, trigger to output.
- TriggerPull request opened or updatedGitHub
- ActionRetrieve relevant ADR ids from Postgres indexPostgres
- ActionLoad accepted ADR bodies from ConfluenceConfluence
- ActionJudge diff against decisions with OpenAIOpenAI
- LogicBranch only when a conflict is detected
- OutputPost grounded conflict warning comment on the PRGitHub
What it does
Guards your accepted architecture decisions at code-review time. On every new pull request it pulls the diff and description, finds the ADRs most relevant to the touched areas, and asks an LLM whether the change appears to violate any accepted decision (for example introducing a banned datastore or bypassing a required boundary).
When to use it
Use it when teams drift from agreed standards between reviews, when reviewers cannot recall every ADR, or when you want a soft, citing guardrail rather than a hard CI block. Pairs with the ADR index sync template.
How it works
- 1A GitHub webhook fires when a pull request is opened or updated.
- 2The flow retrieves candidate ADR ids from the Postgres index using the PR title and changed paths.
- 3It loads the matching accepted ADR bodies from Confluence.
- 4OpenAI compares the diff against the decisions and returns a conflict verdict with the specific ADR cited.
- 5A logic branch posts a warning PR comment only when a real conflict is found; otherwise it stays silent.
Set it up
What you configure once, before turning it on.
- 1Connect GitHubRepos, issues, pull requests, actions.
- 2Connect PostgresAny Postgres URL — query, write, migrate.
- 3Connect ConfluenceSpaces, pages, blueprints.
- 4Connect OpenAIModels, embeddings, files.
- 5Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 6Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 7Test, 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.