AI & RAG
Policy helpdesk auto-reply over email
Watches a policy@ inbox, drafts a cited answer from your Confluence and Drive knowledge base, and either auto-sends it or routes low-confidence questions to a human for review.
How it runs
The automated pipeline, trigger to output.
- TriggerNew email arrives in policy inboxGmail
- ActionRetrieve relevant passages from SupabaseSupabase
- ActionDraft cited answer + confidence score (OpenAI)OpenAI
- LogicBranch on confidence threshold
- OutputAuto-send reply or escalate draft to Slack reviewGmail
What it does
Turns a shared policy mailbox into an AI-first helpdesk. Each inbound email is answered from your indexed documents with sources attached. High-confidence answers send automatically; anything uncertain or sensitive is flagged for a person instead of guessing.
When to use it
Use it when employees or contractors email questions to a central address (benefits, compliance, onboarding) and your team wants to clear the easy 70% automatically while never auto-replying with a shaky answer.
How it works
- 1A new message in the monitored Gmail inbox triggers the run.
- 2The question is matched against the Supabase vector store of Confluence + Drive content.
- 3OpenAI drafts a grounded answer and emits a confidence score.
- 4A logic gate compares confidence to a threshold.
- 5Above threshold, the reply is sent via Gmail with citations; below it, the draft is routed to a Slack review channel for a human to approve or rewrite.
Set it up
What you configure once, before turning it on.
- 1Connect GmailRead, draft, send, label.
- 2Connect ConfluenceSpaces, pages, blueprints.
- 3Connect Google DriveDocs, sheets, slides, files.
- 4Connect SupabaseTables, auth, storage, edge functions.
- 5Connect OpenAIModels, embeddings, files.
- 6Connect SlackChannels, DMs, threads, mentions.
- 7Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 8Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 9Test, 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.