AI & RAG
Draft a grounded Intercom reply from the answer bank on new conversation
On each new inbound Intercom conversation, retrieves the closest vetted answers from the Postgres answer bank, has an LLM compose a cited draft reply.
How it runs
The automated pipeline, trigger to output.
- TriggerIntercom: new conversation createdIntercom
- ActionEmbed customer's opening messageOpenAI
- ActionVector search answer_bank for top matchesPostgres
- LogicBranch: no confident match → tag needs-humanIntercom
- ActionLLM drafts cited reply from retrieved snippetsOpenAI
- OutputPost draft as Intercom internal noteIntercom
What it does
Gives support agents a head start grounded only in approved knowledge. When a customer opens a new conversation, the workflow embeds their question, retrieves the top matching answer-bank entries, and asks an LLM to write a reply using strictly those sources, attaching the Confluence citations. The draft lands as an internal note, never auto-sent.
When to use it
When you want faster first responses without letting a bot improvise. Ideal for teams that trust their curated answer bank but require a human to approve every customer-facing message.
How it works
- 1An Intercom webhook fires when a new conversation is created.
- 2The customer's opening message is embedded with OpenAI.
- 3The workflow runs a vector similarity search against the Postgres answer bank for the top matches above a confidence threshold.
- 4A logic step branches: if no match clears the threshold, it tags the conversation `needs-human` and stops.
- 5Otherwise an LLM drafts a reply constrained to the retrieved snippets, including their source citations.
- 6The draft is posted to the conversation as an internal note for agent review.
Set it up
What you configure once, before turning it on.
- 1Connect IntercomConversations, contacts, articles.
- 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.