# Generate GEO-optimized support replies from Gmail: n8n workflow

> Started by an arriving email, and works across Gmail and Slack. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply...

Source: https://millionrounds.com/workflow/generate-geo-optimized-support-replies-from-gmail (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)

# Generate GEO-optimized support replies from Gmail

Started by an arriving email, and works across Gmail and Slack. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 21 steps, 1 branch: large, and worth reading before you trust it with anything live.

Large Calls a model: OpenAI Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fgenerate-geo-optimized-support-replies-from-gmail)

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

**1** Branch: places the flow splits

**0** Loops or waits

**2** Services it connects to

## The flow

Starts it 2 Model 12 Logic 3 Service 4

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

- 1 **Gmail Trigger** Gmail trigger *Starts it*
- 2 **OpenAI Chat Model - GPT-4o-mini** Lm Chat Open Ai *Model*
- 3 **Memory - Conversation Buffer** Memory Buffer Window *Model*
- 4 **Output Parser - Structured JSON** Output Parser Structured *Model*
- 5 **OpenAI Chat Model - GPT-4o-mini1** Lm Chat Open Ai *Model*
- 6 **Memory - Conversation Buffer1** Memory Buffer Window *Model*
- 7 **Output Parser - Structured JSON1** Output Parser Structured *Model*
- 8 **OpenAI Chat Model - GPT-4o-mini2** Lm Chat Open Ai *Model*
- 9 **Memory - Conversation Buffer2** Memory Buffer Window *Model*
- 10 **Output Parser - Structured JSON2** Output Parser Structured *Model*
- 11 **Error Handler Trigger** Error trigger *Starts it*
- 12 **Extract Email Data** Set *Logic*
- 13 **AI Agent - GEO Identifier** Agent *Model*
- 14 **AI Agent - GEO-Optimized Support** Agent *Model*
- 15 **AI Agent - Email Classification** Agent *Model*
- 16 **Slack: Send Error Alert** Slack *Service*
- 17 **Format Data For Email** Set *Logic*
- 18 **If** If *Logic*
- 19 **Send a message** Gmail *Service*
- 20 **Notify Slack** Slack *Service*
- 21 **Manual Review** Slack *Service*

## How it's built

- **Starts on:** An arriving email
- **Steps:** 21, with 1 branch
- **Size:** Large: read it before trusting it with anything live
- **Connects to:** Gmail, Slack
- **Model:** OpenAI
- **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 and Slack accounts, and a key for OpenAI. 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 OpenAI. 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 21 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 21 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%2Fgenerate-geo-optimized-support-replies-from-gmail)
- **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)[Slack](https://millionrounds.com/workflows?service=Slack#library)

## Workflows like it

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

- [**Automate multi-channel customer support with Gmail** 21 steps · calls a model · Gmail, Google Sheets](https://millionrounds.com/workflow/automate-multi-channel-customer-support-with-gmail)
- [**Automated Slack IT helpdesk with OpenAI and Supabase** 21 steps · calls a model · Slack, Supabase vectors](https://millionrounds.com/workflow/automated-slack-it-helpdesk-with-openai-and-supabase)
- [**Build a Telegram AI assistant with MemMachine and OpenAI** 21 steps · calls a model · Gmail, Google Calendar](https://millionrounds.com/workflow/build-a-telegram-ai-assistant-with-memmachine-and-openai)
- [**AI-powered ticket triage with OpenAI and Postgres** 22 steps · calls a model · Postgres, Slack](https://millionrounds.com/workflow/ai-powered-ticket-triage-with-openai-and-postgres)
- [**Assess GitHub bus-factor risk in GitHub with Claude and Slack** 22 steps · calls a model · Slack](https://millionrounds.com/workflow/assess-github-bus-factor-risk-in-github-with-claude-and-slac)
- [**Route multilingual support requests with DeepL and OpenAI** 20 steps · calls a model · Gmail](https://millionrounds.com/workflow/route-multilingual-support-requests-with-deepl-and-openai)