# Multi-AI Council Research : GPT 5.2, Claude Opus 4.6 & Gemini 3: n8n workflow

> Started by someone opening a chat with it. It calls services over plain HTTP rather than through connectors.

Source: https://millionrounds.com/workflow/multi-ai-council-research-gpt-5-2-claude-opus-4-6-and-gemini (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)

# Multi-AI Council Research: GPT 5.2, Claude Opus 4.6 & Gemini 3

Started by someone opening a chat with it. It calls services over plain HTTP rather than through connectors. It hands the judgement calls to Claude, Gemini and one other. 17 steps, 1 branch: a working afternoon to understand properly.

Medium Calls a model: Claude, Gemini

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fmulti-ai-council-research-gpt-5-2-claude-opus-4-6-and-gemini)

**17 steps** Medium: a working afternoon

**1** Branch: places the flow splits

**0** Loops or waits

**0** Services by connector: it calls them over plain HTTP

## The flow

Starts it 1 Model 12 Logic 4

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

- 1 **When chat message received** Chat trigger *Starts it*
- 2 **Google Gemini Chat Model** Lm Chat Google Gemini *Model*
- 3 **Structured Output Parser** Output Parser Structured *Model*
- 4 **OpenAI Chat Model** Lm Chat Open Ai *Model*
- 5 **Anthropic Chat Model** Lm Chat Anthropic *Model*
- 6 **Google Gemini Chat Model1** Lm Chat Google Gemini *Model*
- 7 **Google Gemini Chat Model2** Lm Chat Google Gemini *Model*
- 8 **Search Query Optimizer** Chain Llm *Model*
- 9 **ChatGPT 5.2** Chain Llm *Model*
- 10 **Claude Opus 4.6** Chain Llm *Model*
- 11 **Gemini 3 Pro** Chain Llm *Model*
- 12 **Multi-Response Aggregator** Chain Llm *Model*
- 13 **Search?** If *Logic*
- 14 **ChatGPT Result** Set *Logic*
- 15 **Claude Result** Set *Logic*
- 16 **Gemini Result** Set *Logic*
- 17 **Chat** Chat *Model*

## How it's built

- **Starts on:** Someone opening a chat with it
- **Steps:** 17, with 1 branch
- **Size:** Medium: a working afternoon
- **Connects to:** Nothing by connector; it calls services over plain HTTP
- **Model:** Claude, Gemini, OpenAI

## Questions

What does it need to run?

An n8n account, and a key for Claude and Gemini. You connect your own accounts after importing it; none are included.

What starts it?

It starts on someone opening a chat with it.

Does it use AI?

Yes. It calls Claude, Gemini and OpenAI. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Plan an afternoon. 17 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 17 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%2Fmulti-ai-council-research-gpt-5-2-claude-opus-4-6-and-gemini)
- **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.

## Workflows like it

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

- [**# ⃣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)
- [**AI-powered research assistant with Linear and Scrapeless** 17 steps · calls a model · Linear](https://millionrounds.com/workflow/ai-powered-research-assistant-with-linear-and-scrapeless)
- [**AI-powered stock analysis assistant with Telegram and Claude** 17 steps · calls a model · Telegram](https://millionrounds.com/workflow/ai-powered-stock-analysis-assistant-with-telegram-and-claude)
- [**AI-powered stock analysis with Gmail** 17 steps · calls a model · Gmail, Supabase vectors](https://millionrounds.com/workflow/ai-powered-stock-analysis-with-gmail)
- [**AI-powered web research in Google Sheets with OpenAI** 17 steps · calls a model · n8n data table](https://millionrounds.com/workflow/ai-powered-web-research-in-google-sheets-with-openai)
- [**Automate Instagram profile analysis with Airtop and OpenAI** 17 steps · calls a model · Google Sheets](https://millionrounds.com/workflow/automate-instagram-profile-analysis-with-airtop-and-openai)