AI & RAG
ADR Index Sync: scheduled Confluence-to-Postgres embedding refresh
On a schedule, pulls new and edited ADR pages from Confluence, generates embeddings, and upserts them into the Postgres decision index so the answerbot always retrieves current…
How it runs
The automated pipeline, trigger to output.
- TriggerScheduled refresh timer fires
- ActionFetch ADR pages changed since watermark from ConfluenceConfluence
- LogicExit early if no pages changed
- ActionGenerate embeddings for changed pages with OpenAIOpenAI
- OutputUpsert vectors and metadata into Postgres indexPostgres
What it does
Keeps the retrieval index behind your ADR answerbot fresh. It scans the Confluence ADR space for pages created or changed since the last run, re-embeds them, and upserts the vectors plus metadata into Postgres so searches never return stale or missing decisions.
When to use it
Run this as the ingestion backbone for any ADR RAG setup. Use it when ADRs change often, when a new decision should be answerable within minutes, or when you want embeddings recomputed without a manual reindex.
How it works
- 1A scheduled timer fires (e.g. every 30 minutes).
- 2The flow queries Confluence for ADR pages with a lastModified newer than the stored watermark.
- 3A branch checks whether any pages changed; if none, it exits cleanly.
- 4For each changed page, OpenAI produces an embedding of the chunked body.
- 5The embeddings, page id, version, status, and title upsert into the Postgres index, and the watermark advances.
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.