AI & RAG
Freeze and Index a Compliance Policy Corpus into pgvector
Snapshots approved policy pages from Notion, chunks and embeds them, and writes a versioned, frozen index to Supabase pgvector that downstream answer bots retrieve from.
How it runs
The automated pipeline, trigger to output.
- TriggerScheduled re-index on policy review cadence
- ActionFetch approved policy pages from Notion databaseNotion
- LogicChunk pages on heading boundaries for citable spans
- ActionGenerate chunk embeddings with OpenAIOpenAI
- OutputWrite version-tagged chunks and vectors to Supabase pgvectorSupabase
What it does
Builds the searchable foundation every grounded answer bot needs. It pulls a defined set of approved policy pages from Notion, splits them into citable chunks, generates embeddings, and writes them to a version-stamped table in Supabase. The result is a frozen corpus snapshot you can point answer bots at without drift.
When to use it
Run this once per policy review cycle — after Compliance signs off on a new revision — so all answer bots share one immutable source of truth. Use it instead of live-querying Notion so answers can't change mid-cycle.
How it works
- 1A scheduled run kicks off the re-index on your review cadence.
- 2Approved policy pages are fetched from a designated Notion database.
- 3Each page is chunked with heading-aware boundaries so citations map to real sections.
- 4OpenAI generates embeddings for every chunk.
- 5Chunks, embeddings, and a corpus version tag are written to Supabase pgvector, leaving the prior version intact for rollback.
Set it up
What you configure once, before turning it on.
- 1Connect NotionPages, databases, comments.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect SupabaseTables, auth, storage, edge functions.
- 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.