# Draft grounded Gmail support replies from a Notion KB: n8n workflow

> Started by an arriving email, and works across Gmail, Notion and in-memory vectors. It puts Groq behind a retrieval step, so answers are drawn from...

Source: https://millionrounds.com/workflow/draft-grounded-gmail-support-replies-from-a-notion-kb (Millionrounds; every figure on the page links to its filing or article)

[Automation library](https://millionrounds.com/workflows) · [Customer support](https://millionrounds.com/workflows?category=Customer+support#library)

# Draft grounded Gmail support replies from a Notion KB

Started by an arriving email, and works across Gmail, Notion and in-memory vectors. It puts Groq behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 23 steps, 3 branches: large, and worth reading before you trust it with anything live.

Large Calls a model: Groq Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fdraft-grounded-gmail-support-replies-from-a-notion-kb)

**23 steps** Large: read it before trusting it with anything live

**3** Branches: places the flow splits

**0** Loops or waits

**3** Services it connects to

## The flow

Starts it 2 Model 11 Logic 7 Service 3

The steps in the order they run, from what starts it.

- 1 **Run KB Ingestion** Manual trigger *Starts it*
- 2 **Split Article Into Chunks** Text Splitter Recursive Character Text Splitter *Model*
- 3 **When Support Email Arrives** Gmail trigger *Starts it*
- 4 **Groq Triage Model** Lm Chat Groq *Model*
- 5 **Groq Draft Model** Lm Chat Groq *Model*
- 6 **Embed Articles With Cohere** Embeddings Cohere *Model*
- 7 **Embed Query With Cohere** Embeddings Cohere *Model*
- 8 **Rerank Matches With Cohere** Reranker Cohere *Model*
- 9 **Get KB Articles** Notion *Service*
- 10 **Load Article Text** Document Default Data Loader *Model*
- 11 **Normalize Email** Set *Logic*
- 12 **Classify Inquiry** Text Classifier *Model*
- 13 **Draft Grounded Reply** Chain Llm *Model*
- 14 **Store KB Vectors** Vector Store In Memory *Model*
- 15 **Retrieve From KB** Vector Store In Memory *Model*
- 16 **Check If Published** If *Logic*
- 17 **Check If Answered** If *Logic*
- 18 **Bundle Retrieved Sources** Code *Logic*
- 19 **Get Article Body** Notion *Service*
- 20 **Build Reply With Sources** Set *Logic*
- 21 **Check Retrieval Confidence** If *Logic*
- 22 **Assemble Article Documents** Code *Logic*
- 23 **Save Draft For Review** Gmail *Service*

## How it's built

- **Starts on:** An arriving email
- **Steps:** 23, with 3 branches
- **Size:** Large: read it before trusting it with anything live
- **Connects to:** Gmail, Notion, in-memory vectors
- **Model:** Groq
- **Retrieval:** Answers are drawn from documents you supply, not from the model alone

## Questions

What does it need to run?

An n8n account, plus your own Gmail, Notion and in-memory vectors accounts, and a key for Groq. You connect your own accounts after importing it; none are included.

What starts it?

It starts on an arriving email.

Does it use AI?

Yes. It calls Groq. Its answers draw on documents you give it, not on the model alone. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Take your time. At 23 steps it is large: read it before trusting it with anything live.

How do I import it?

Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts.

**Before you run it**

Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 23 steps before you point it at anything that matters.

## Run it in n8n

- **Create your n8n account** Free to start. n8n is where the workflow runs. [Create an n8n account ↗](https://millionrounds.com/n8n)
- **Download the workflow** Free with a Millionrounds account. [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fdraft-grounded-gmail-support-replies-from-a-notion-kb)
- **Paste it into n8n** Open a new workflow in n8n and paste. Then connect your own accounts.

Stored with the author's traces removed: canvas notes, instance identifiers, saved credential names and any live document they had left behind.

## Connects to

Each opens the other workflows that use it.

[Gmail](https://millionrounds.com/workflows?service=Gmail#library)[Notion](https://millionrounds.com/workflows?service=Notion#library)[in-memory vectors](https://millionrounds.com/workflows?service=in-memory+vectors#library)

## Workflows like it

Also customer support, with the same services where possible, closest in size first.

- [**AI email support system: Gmail, Gemini, GPT-4, Slack & Google** 23 steps · calls a model · Gmail, Google Drive](https://millionrounds.com/workflow/ai-email-support-system-gmail-gemini-gpt-4-slack-and-google)
- [**Create a WhatsApp customer support bot with OpenAI** 23 steps · calls a model · Gmail, Google Calendar](https://millionrounds.com/workflow/create-a-whatsapp-customer-support-bot-with-openai)
- [**Route and triage multi-channel support tickets with OpenAI** 23 steps · calls a model · Gmail, Google Sheets](https://millionrounds.com/workflow/route-and-triage-multi-channel-support-tickets-with-openai)
- [**SEO FAQ generator for websites with Google Sheets** 24 steps · calls a model · Gmail, Google Sheets](https://millionrounds.com/workflow/seo-faq-generator-for-websites-with-google-sheets)
- [**Route support tickets with SLA and Slack** 22 steps · Gmail, Slack](https://millionrounds.com/workflow/route-support-tickets-with-sla-and-slack)
- [**Route website chat visitors to Calendly booking, FAQs, and Gmail** 24 steps · Gmail](https://millionrounds.com/workflow/route-website-chat-visitors-to-calendly-booking-faqs-and-gma)