AI & RAG
Incremental Runbook Re-Index on Confluence Page Update
Listens for Confluence page edits, re-chunks only the changed runbook page into heading-anchored sections, re-embeds them, and upserts the vectors in Postgres so the answer bot…
How it runs
The automated pipeline, trigger to output.
- TriggerConfluence page created or updated webhook firesConfluence
- ActionFetch page body and split into heading-anchored sectionsConfluence
- ActionEmbed each changed section with OpenAIOpenAI
- ActionUpsert section vectors in Postgres by page ID, version, and anchorPostgres
- LogicPrune vectors for sections removed from the page
What it does
Keeps the RAG index fresh by reacting to individual Confluence edits instead of nightly full rebuilds. When a runbook page changes, it re-chunks that single page by heading, generates fresh embeddings, and upserts them into the vector store keyed by page ID, version, and heading anchor.
When to use it
Use it when your runbooks change often and a stale index would hand engineers outdated rollback or escalation steps. It also keeps embedding costs low by only reprocessing what actually changed.
How it works
- 1A Confluence webhook fires when a runbook page is created or updated.
- 2The flow fetches the page body and splits it into sections at each heading, capturing the anchor and version number.
- 3Each section is embedded via OpenAI.
- 4Vectors are upserted into Postgres keyed by page ID and heading anchor; sections deleted from the page are pruned.
- 5The run records the new version so citations always resolve to the live source.
Set it up
What you configure once, before turning it on.
- 1Connect ConfluenceSpaces, pages, blueprints.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect PostgresAny Postgres URL — query, write, migrate.
- 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.