AI & RAG
Draft cited manual answers for inbound support tickets in Zendesk
Reads incoming equipment support tickets, retrieves the matching manual passages, and drafts a reply with page citations for an agent to review before sending.
How it runs
The automated pipeline, trigger to output.
- TriggerNew technical support ticket created in ZendeskZendesk
- ActionExtract equipment model and question from ticketOpenAI
- ActionRetrieve matching manual passages from SupabaseSupabase
- LogicRoute low-confidence retrievals to human-only tag
- ActionDraft grounded reply with inline page citationsOpenAI
- OutputAttach cited draft as internal note on the ticketZendesk
What it does
Turns inbound technical support tickets into ready-to-review draft replies. It interprets the customer's equipment question, retrieves grounded passages from the versioned manual index, and writes a citation-backed answer as an internal draft so a human agent can approve and send.
When to use it
When your support queue is full of repetitive 'what is the spec / how do I' equipment questions and you want agents reviewing accurate drafts instead of researching from scratch. Keeps a human in the loop for liability while removing the lookup work.
How it works
- 1A new ticket arrives in Zendesk and fires the trigger.
- 2The flow extracts the equipment model and the core question from the ticket body.
- 3The question is matched against the Supabase manual vector store, returning passages with page numbers.
- 4OpenAI drafts an answer grounded only in those passages, with inline page citations.
- 5A logic step routes low-confidence retrievals to a human-only tag instead of drafting.
- 6The draft reply with citations is attached to the ticket as an internal note for agent review.
Set it up
What you configure once, before turning it on.
- 1Connect ZendeskTickets, queues, knowledge base.
- 2Connect SupabaseTables, auth, storage, edge functions.
- 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
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.
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…
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.
Re-Index API Specs on GitLab Merge to Keep the Answer Bot Fresh
Watches GitLab merges to your API repo, detects changed OpenAPI specs and changelog files, re-chunks and re-embeds only what changed.
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.