AI & RAG
ADR Answer Bot for Slack with Citations
Answers architecture questions in Slack by retrieving relevant Architecture Decision Records, citing each ADR by number, and warning when a cited decision has been superseded.
How it runs
The automated pipeline, trigger to output.
- TriggerEngineer mentions bot with a question in SlackSlack
- ActionRetrieve top ADRs from Confluence knowledge baseConfluence
- LogicSplit candidates into Accepted vs Superseded by status
- ActionGenerate cited answer from accepted ADR textOpenAI
- OutputReply in-thread with citations and supersession flagsSlack
What it does
Lets engineers ask architecture questions in Slack and get a grounded answer drawn only from your Architecture Decision Records. Every claim cites the ADR it came from (e.g. ADR-0025), and if a retrieved ADR is marked Superseded the bot flags it and points to the replacement instead of answering from stale guidance.
When to use it
When your team keeps ADRs in Confluence but nobody reads them, and the same "why did we decide X" questions get asked in channels every week. Good for onboarding, design reviews, and settling debates without a maintainer playing librarian.
How it works
- 1An engineer mentions the bot in Slack with a question.
- 2The query is embedded and matched against the ADR knowledge base in Confluence to pull the top candidate records.
- 3A logic step inspects each candidate's status field and separates Accepted from Superseded or Deprecated decisions.
- 4OpenAI composes a grounded answer using only the accepted ADR text, attaching the ADR number and link to each statement.
- 5The bot replies in-thread; if any superseded ADR was relevant, it adds a callout naming the record that replaced it.
Set it up
What you configure once, before turning it on.
- 1Connect SlackChannels, DMs, threads, mentions.
- 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
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.