# Route and analyze customer feedback with Qwen3-VL and Tally: n8n workflow

> Started by an event in a connected app, and works across Discord and Postgres. It hands the judgement calls to OpenAI.

Source: https://millionrounds.com/workflow/route-and-analyze-customer-feedback-with-qwen3-vl-and-tally (Millionrounds; every figure on the page links to its filing or article)

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

# Route and analyze customer feedback with Qwen3-VL and Tally

Started by an event in a connected app, and works across Discord and Postgres. It hands the judgement calls to OpenAI. 26 steps, 2 branches: large, and worth reading before you trust it with anything live.

Large Calls a model: OpenAI

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Froute-and-analyze-customer-feedback-with-qwen3-vl-and-tally)

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

**2** Branches: places the flow splits

**0** Loops or waits

**2** Services it connects to

## The flow

Starts it 1 Model 9 Logic 13 Service 3

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

- 1 **Tally Trigger** Tally trigger *Starts it*
- 2 **Routing LLM** Lm Chat Open Ai *Model*
- 3 **Sentiment LLM** Lm Chat Open Ai *Model*
- 4 **Sentiment Parser** Output Parser Structured *Model*
- 5 **Classification LLM** Lm Chat Open Ai *Model*
- 6 **Classification Parser** Output Parser Structured *Model*
- 7 **Route Parser** Output Parser Structured *Model*
- 8 **Field Mapping** Set *Logic*
- 9 **Decision Logic** Chain Llm *Model*
- 10 **Sentiment Analysis** Chain Llm *Model*
- 11 **Text Classification** Chain Llm *Model*
- 12 **If** If *Logic*
- 13 **AI Results Merge** Merge *Logic*
- 14 **Channel Router** Switch *Logic*
- 15 **Fetch Image** Http Request *Service*
- 16 **Empty Keywords Handler** Set *Logic*
- 17 **Data Aggregation** Aggregate *Logic*
- 18 **#general-inquiries** Set *Logic*
- 19 **#happy-customers** Set *Logic*
- 20 **#support-urgent** Set *Logic*
- 21 **Image Keyword Extraction** Code *Logic*
- 22 **Image Results Merge** Merge *Logic*
- 23 **Save to PostgreSQL** Postgres *Service*
- 24 **Build Discord Message** Merge *Logic*
- 25 **Format Embed Data** Code *Logic*
- 26 **Send Discord Notification** Discord *Service*

## How it's built

- **Starts on:** An event in a connected app
- **Steps:** 26, with 2 branches
- **Size:** Large: read it before trusting it with anything live
- **Connects to:** Discord, Postgres
- **Model:** OpenAI

## Questions

What does it need to run?

An n8n account, plus your own Discord and Postgres 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. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Take your time. At 26 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 26 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%2Froute-and-analyze-customer-feedback-with-qwen3-vl-and-tally)
- **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.

[Discord](https://millionrounds.com/workflows?service=Discord#library)[Postgres](https://millionrounds.com/workflows?service=Postgres#library)

## Workflows like it

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

- [**Automate blog creation & publishing with Gemini** 26 steps · calls a model · Discord, Google Sheets](https://millionrounds.com/workflow/automate-blog-creation-and-publishing-with-gemini)
- [**News collection & multi-platform publishing with OpenAI** 26 steps · calls a model · Discord, Gmail](https://millionrounds.com/workflow/news-collection-and-multi-platform-publishing-with-openai)
- [**Route weather-based delivery holds with Open-Meteo and Gemini** 26 steps · calls a model · Postgres, Slack](https://millionrounds.com/workflow/route-weather-based-delivery-holds-with-open-meteo-and-gemin)
- [**Automated Instagram content creation from trending posts** 27 steps · calls a model · Postgres, Telegram](https://millionrounds.com/workflow/automated-instagram-content-creation-from-trending-posts)
- [**Generate Instagram content from top trends with OpenAI** 27 steps · calls a model · Postgres, Telegram](https://millionrounds.com/workflow/generate-instagram-content-from-top-trends-with-openai)
- [**Maintain RAG embeddings with OpenAI and Postgres** 27 steps · calls a model · Postgres, in-memory vectors](https://millionrounds.com/workflow/maintain-rag-embeddings-with-openai-and-postgres)