AI & RAG
Answer Intercom 'how do I' questions with a timestamped Loom clip
When a customer asks a how-to question in Intercom, retrieve the most relevant passage from your indexed Loom walkthroughs and reply with a short answer plus a deep link…
How it runs
The automated pipeline, trigger to output.
- TriggerNew Intercom message receivedIntercom
- LogicClassify as procedural how-to question
- ActionRetrieve matching Loom passages from pgvectorPostgres
- LogicBranch on retrieval confidence
- ActionDraft grounded answer with OpenAIOpenAI
- OutputReply in Intercom with timestamped Loom linkIntercom
What it does
Watches incoming Intercom conversations for 'how do I' style questions and answers them from your Loom SOP library. It retrieves the best-matching transcript passages, drafts a concise answer grounded only in those passages, and attaches a Loom link with a `?t=` timestamp so the customer lands on the exact step. When confidence is low it tags the conversation for a human instead of guessing.
When to use it
Use it on a support inbox where the same procedural questions recur and you already have Loom walkthroughs covering them. It deflects repetitive tickets while still pointing customers to authoritative video, not hallucinated text.
How it works
- 1A new Intercom conversation or reply triggers the flow.
- 2A classifier decides whether the message is a procedural 'how do I' question; non-procedural messages are skipped.
- 3The question is embedded and matched against the Loom transcript vectors in Postgres.
- 4A retrieval confidence check branches: strong match continues, weak match routes to a human.
- 5OpenAI drafts a grounded answer citing the retrieved passages.
- 6The flow posts the reply to Intercom with a timestamped Loom deep link.
Set it up
What you configure once, before turning it on.
- 1Connect IntercomConversations, contacts, articles.
- 2Connect PostgresAny Postgres URL — query, write, migrate.
- 3Connect OpenAIModels, embeddings, files.
- 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.