AI & RAG
Weekly Stale-RFC Digest From Code-Doc Drift
Weekly, cross-references Confluence RFCs against the current GitHub code they describe, flags RFCs whose implementation has diverged.
How it runs
The automated pipeline, trigger to output.
- TriggerWeekly schedule fires
- ActionRetrieve current GitHub code per RFCGitHub
- ActionCompare doc vs code, score driftOpenAI
- LogicFilter and rank RFCs over drift threshold
- OutputEmail leads the stale-RFC digestGmail
What it does
Surfaces documentation rot before it misleads anyone. Each week it walks your indexed RFCs, pulls the GitHub code each one references, and uses retrieval plus comparison to detect where the implementation no longer matches the documented design. It ranks the mismatches and sends engineering leads a single digest of the most-diverged RFCs with links to both sides.
When to use it
When RFCs are written once and rarely updated while code keeps moving, leaving an answer-bot grounded in outdated truth. Run alongside the index builder.
How it works
- 1A weekly schedule fires the audit.
- 2The flow iterates RFC entries and retrieves the matching current GitHub source for each.
- 3OpenAI compares documented design against actual code and assigns a drift score with cited evidence.
- 4A logic step filters to RFCs exceeding the drift threshold and sorts by severity.
- 5The flow emails engineering leads a ranked digest, each entry linking the RFC page and the diverged code.
Set it up
What you configure once, before turning it on.
- 1Connect ConfluenceSpaces, pages, blueprints.
- 2Connect GitHubRepos, issues, pull requests, actions.
- 3Connect OpenAIModels, embeddings, files.
- 4Connect GmailRead, draft, send, label.
- 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
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.
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…
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.
Re-Index API Specs on GitLab Merge to Keep the Answer Bot Fresh
Watches GitLab merges to your API repo, detects changed OpenAPI specs and changelog files, re-chunks and re-embeds only what changed.
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.