# AI-powered customer feedback analysis & routing: n8n workflow

> Started by an event in a connected app, and works across Gmail and Notion. It puts OpenAI behind a retrieval step, so answers are drawn from documents you...

Source: https://millionrounds.com/workflow/ai-powered-customer-feedback-analysis-and-routing (Millionrounds; every figure on the page links to its filing or article)

[Automation library](https://millionrounds.com/workflows) · [Research and reporting](https://millionrounds.com/workflows?category=Research+and+reporting#library)

# AI-powered customer feedback analysis & routing

Started by an event in a connected app, and works across Gmail and Notion. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 18 steps: a working afternoon to understand properly.

Medium Calls a model: OpenAI Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fai-powered-customer-feedback-analysis-and-routing)

**18 steps** Medium: a working afternoon

**0** Branches: places the flow splits

**0** Loops or waits

**2** Services it connects to

## The flow

Starts it 1 Model 9 Logic 1 Service 7

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

- 1 **Manual Trigger: Start VOC Analysis** Manual trigger *Starts it*
- 2 **Config: Set LLM for Agents** Lm Chat Open Ai *Model*
- 3 **Config: Set Agent Memory** Memory Buffer Window *Model*
- 4 **Tool: Get Gmail Messages** Gmail Tool *Service*
- 5 **Tool: Get Pipedrive Notes** Pipedrive Tool *Service*
- 6 **Tool: Get Zendesk Tickets** Zendesk Tool *Service*
- 7 **Tool: Search Slack Messages Export to Sheets** Slack Tool *Service*
- 8 **AI: Structure Key Signals** Output Parser Structured *Model*
- 9 **AI: Structure Clustered Topics Export to Sheets** Output Parser Structured *Model*
- 10 **Tool: Create Zendesk Ticket** Zendesk Tool *Service*
- 11 **Tool: Send Email Alert** Gmail Tool *Service*
- 12 **Tool: Create Notion Page** Notion Tool *Service*
- 13 **Set: Initial Parameters** Set *Logic*
- 14 **AI: Structure Feedback Data** Output Parser Structured *Model*
- 15 **AI Agent: Gather Customer Feedback** Agent *Model*
- 16 **AI Chain: Extract Key Signals** Chain Llm *Model*
- 17 **AI Chain: Cluster Signals into Topics** Chain Llm *Model*
- 18 **AI Agent: Route Topics to Actions** Agent *Model*

## How it's built

- **Starts on:** An event in a connected app
- **Steps:** 18
- **Size:** Medium: a working afternoon
- **Connects to:** Gmail, Notion
- **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 Notion accounts, and a key for OpenAI. You connect your own accounts after importing it; none are included.

What starts it?

It starts on an event in a connected app.

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?

Plan an afternoon. 18 steps is enough that you should read each one before running it.

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 18 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%2Fai-powered-customer-feedback-analysis-and-routing)
- **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)

## Workflows like it

Also research and reporting, with the same services where possible, closest in size first.

- [**AI-powered damage reporting tool for logistics with Gmail** 18 steps · calls a model · Gmail, Telegram](https://millionrounds.com/workflow/ai-powered-damage-reporting-tool-for-logistics-with-gmail)
- [**Analyze competitor strategy from YouTube & RSS with Gemini** 18 steps · calls a model · Apify, Notion](https://millionrounds.com/workflow/analyze-competitor-strategy-from-youtube-and-rss-with-gemini)
- [**Build a document-upload RAG chatbot with OpenAI and Pinecone** 18 steps · calls a model · Gmail, Pinecone](https://millionrounds.com/workflow/build-a-document-upload-rag-chatbot-with-openai-and-pinecone)
- [**Generate fact-checked research reports with Bright Data** 18 steps · calls a model · Gmail, Google Sheets](https://millionrounds.com/workflow/generate-fact-checked-research-reports-with-bright-data)
- [**Weekly AI YouTube summary（OpenAI+YC+Google Deepmind）** 18 steps · calls a model · Gmail, RSS](https://millionrounds.com/workflow/weekly-ai-youtube-summary-openai-yc-google-deepmind)
- [**# ⃣Nostr #damus AI powered reporting + Gmail + Telegram** 17 steps · calls a model · Gmail, Telegram](https://millionrounds.com/workflow/nostr-damus-ai-powered-reporting-gmail-telegram)