AI & RAG
Nightly postmortem indexer for runbook retrieval
On a nightly schedule, pulls new and updated incident postmortems from Confluence, chunks and embeds them.
How it runs
The automated pipeline, trigger to output.
- TriggerNightly schedule fires
- ActionQuery Confluence for postmortems modified since last syncConfluence
- ActionChunk pages and generate embeddingsOpenAI
- ActionUpsert vectors and citation metadata into PostgresPostgres
- OutputPost indexing summary to Slack ops channelSlack
What it does
Keeps the knowledge base behind your on-call RAG assistant current. Each night it ingests postmortems edited or created since the last run, splits them into retrievable chunks, generates embeddings, and upserts them into the pgvector store — with metadata for citation links.
When to use it
Run this as the foundation under any postmortem-RAG workflow. Use it when postmortems live in Confluence and get written continuously, so manual re-indexing isn't realistic. It is the upstream job the answer bots depend on.
How it works
- 1A nightly schedule triggers the run.
- 2The workflow queries Confluence for postmortem pages modified since the last successful sync timestamp.
- 3Each page is cleaned, chunked, and passed through an embedding model.
- 4Vectors plus source metadata (page ID, title, URL) are upserted into Postgres, replacing stale chunks for updated pages.
- 5A short summary of pages indexed and skipped is posted to a Slack ops channel for an audit trail.
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.
- 4Connect SlackChannels, DMs, threads, mentions.
- 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
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.
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.
Grounded reply suggestions for inbound sales email
Reads inbound prospect emails, retrieves the matching answers from your Coda hub.
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.
On-Call Spec Answerer from Dropbox Engineering Corpus
Answers on-call questions posted in a Slack channel by retrieving the most relevant Dropbox engineering specs and replying with a grounded, source-cited answer in the thread.
Agentic Deep-Dive API Researcher for Hard Spec Questions
An agent fielded via webhook that answers multi-part API questions by iteratively searching OpenAPI specs, changelogs, and Confluence runbooks.
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.