AI & RAG
Runbook Answer Bot with Required Citations in Slack
Answers on-call and ops questions in Slack by grounding every reply in your Confluence + Drive runbook corpus, and refuses to answer when no supporting source exists.
How it runs
The automated pipeline, trigger to output.
- TriggerSlack message or @mention in #ops-helpSlack
- ActionEmbed question and retrieve top runbook passagesPostgres
- LogicGate on retrieval confidence; reply 'not documented' if low
- ActionCompose grounded answer with source IDsOpenAI
- OutputPost answer with inline citations to Slack threadSlack
What it does
Turns a Slack channel into a runbook help desk. When someone asks a procedural question, the agent retrieves the most relevant passages from your indexed Confluence pages and Google Drive docs, drafts an answer, and posts it back with inline citations linking to each source. If retrieval surfaces nothing above the confidence threshold, it says so plainly instead of guessing.
When to use it
Use it when on-call engineers, support agents, or new hires keep asking 'how do I...' questions that are already documented but hard to find. It cuts repeated interruptions to senior staff and keeps answers traceable to a canonical doc.
How it works
- 1A Slack message in the watch channel (or an app mention) triggers the flow.
- 2The question is embedded and matched against the runbook vector index in Postgres.
- 3A logic gate checks retrieval score: below threshold, it short-circuits to a 'not documented' reply.
- 4OpenAI composes an answer constrained to the retrieved passages, emitting source IDs.
- 5The bot posts the answer to the Slack thread with clickable citations to each Confluence or Drive source.
Set it up
What you configure once, before turning it on.
- 1Connect SlackChannels, DMs, threads, mentions.
- 2Connect PostgresAny Postgres URL — query, write, migrate.
- 3Connect OpenAIModels, embeddings, files.
- 4Connect ConfluenceSpaces, pages, blueprints.
- 5Connect Google DriveDocs, sheets, slides, files.
- 6Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 7Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 8Test, 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.