AI & RAG
Answer internal support questions in Slack from Confluence and tickets
Lets staff ask support or product questions in a Slack channel and replies in-thread with an answer grounded in Confluence docs and historical Zendesk tickets, with citations.
How it runs
The automated pipeline, trigger to output.
- TriggerBot mentioned in Slack support channelSlack
- ActionRetrieve relevant docs + tickets from SupabaseSupabase
- LogicRelevance check: answer or report no match
- ActionSynthesize source-constrained answer with OpenAIOpenAI
- OutputReply in Slack thread with citationsSlack
What it does
Acts as an internal knowledge bot. When a teammate asks a question in a designated Slack channel, it retrieves the relevant product docs and resolved tickets and answers right in the thread, citing exactly where each fact came from so people can verify it.
When to use it
For support, sales, and success teams that constantly ping each other with "how does X work?" questions. Deflects repeat questions away from senior engineers and keeps tribal knowledge searchable.
How it works
- 1A mention of the bot in Slack (or a message in its channel) fires the trigger.
- 2The question is embedded and used to search a Supabase vector index built from Confluence and past Zendesk tickets.
- 3A relevance check decides whether to answer or reply that nothing solid was found.
- 4OpenAI synthesizes an answer constrained to the retrieved sources.
- 5The bot replies in-thread with the answer and clickable source links.
Set it up
What you configure once, before turning it on.
- 1Connect SlackChannels, DMs, threads, mentions.
- 2Connect ConfluenceSpaces, pages, blueprints.
- 3Connect SupabaseTables, auth, storage, edge functions.
- 4Connect OpenAIModels, embeddings, files.
- 5Connect ZendeskTickets, queues, knowledge base.
- 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.