AI & RAG
Suggest grounded answers to live Intercom chats from product docs
On each inbound Intercom message, searches product docs and resolved conversations and surfaces a suggested, source-linked answer to the agent in real time.
How it runs
The automated pipeline, trigger to output.
- TriggerNew inbound Intercom messageIntercom
- ActionSearch Supabase store of docs + past conversationsSupabase
- LogicConfidence gate: suggest or stay silent
- ActionDraft grounded answer with OpenAIOpenAI
- OutputPost suggestion as private note in IntercomIntercom
What it does
Gives front-line chat agents an instant, cited answer suggestion the moment a customer types a question, without leaving the inbox. It reads the live message, looks up the supporting documentation and similar past conversations, and proposes a reply the agent can accept, edit, or ignore.
When to use it
For high-volume live chat where agents juggle several conversations and need fast, accurate recall of product behavior. Ideal when answer quality matters but a human stays in the loop on every send.
How it works
- 1A new inbound message in an Intercom conversation fires the trigger.
- 2The message text is embedded and matched against a Supabase store of Confluence docs and resolved Intercom threads.
- 3A confidence gate decides whether to suggest an answer or stay silent on low-relevance hits.
- 4OpenAI drafts a concise reply grounded strictly in the retrieved passages.
- 5The suggestion plus source links is posted as a private note on the conversation for the agent.
Set it up
What you configure once, before turning it on.
- 1Connect IntercomConversations, contacts, articles.
- 2Connect ConfluenceSpaces, pages, blueprints.
- 3Connect SupabaseTables, auth, storage, edge functions.
- 4Connect OpenAIModels, embeddings, files.
- 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
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.