AI & RAG
ADR Staleness Audit: flag decisions overtaken by reality
On a schedule, scans accepted ADRs, uses an LLM to assess which are likely stale or contradicted by newer decisions in the index.
How it runs
The automated pipeline, trigger to output.
- TriggerMonthly staleness audit schedule fires
- ActionLoad accepted ADRs and metadata from PostgresPostgres
- ActionFetch ADR bodies from ConfluenceConfluence
- ActionScore each ADR for staleness with OpenAIOpenAI
- LogicKeep only ADRs above the staleness threshold
- OutputOpen Linear review tickets for flagged ADR ownersLinear
What it does
Finds Architecture Decision Records that have quietly gone out of date. It reviews accepted ADRs against newer accepted decisions in the index, asks an LLM to flag likely-stale or superseded-in-practice records, and creates a Linear ticket so an owner can confirm, update, or formally supersede each one.
When to use it
Use it when your ADR space accumulates decisions that nobody revisits, when "accepted" records silently contradict current practice, or when you need a recurring hygiene pass that turns into actionable owner tasks rather than a report nobody reads.
How it works
- 1A monthly schedule starts the audit.
- 2The flow loads all accepted ADRs and their metadata from the Postgres index.
- 3It fetches the bodies of accepted ADRs from Confluence for full context.
- 4OpenAI scores each ADR for staleness, citing the newer decision or signal that contradicts it.
- 5A logic branch keeps only ADRs above a staleness threshold.
- 6For each flagged ADR, a Linear review ticket is opened and assigned to the recorded owner.
Set it up
What you configure once, before turning it on.
- 1Connect PostgresAny Postgres URL — query, write, migrate.
- 2Connect ConfluenceSpaces, pages, blueprints.
- 3Connect OpenAIModels, embeddings, files.
- 4Connect LinearIssues, projects, cycles, triage.
- 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.