# Generate multi-agent AI research reports with OpenAI: n8n workflow

> Started by another system calling it. It calls services over plain HTTP rather than through connectors. It hands the judgement calls to OpenAI.

Source: https://millionrounds.com/workflow/generate-multi-agent-ai-research-reports-with-openai (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)

# Generate multi-agent AI research reports with OpenAI

Started by another system calling it. It calls services over plain HTTP rather than through connectors. It hands the judgement calls to OpenAI. 24 steps, 3 loops or waits: 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%2Fgenerate-multi-agent-ai-research-reports-with-openai)

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

**0** Branches: places the flow splits

**3** Loops or waits

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

## The flow

Starts it 3 Model 10 Logic 9 Service 2

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

- 1 **Webhook - Research Topic Intake** Webhook *Starts it*
- 2 **Schedule - Weekly Research Trigger** Schedule trigger *Starts it*
- 3 **OpenAI Model - Agent A** Lm Chat Open Ai *Model*
- 4 **OpenAI Model - Agent B** Lm Chat Open Ai *Model*
- 5 **OpenAI Model - Agent C** Lm Chat Open Ai *Model*
- 6 **OpenAI Model - Critique Agent** Lm Chat Open Ai *Model*
- 7 **OpenAI Model - Synthesis Agent** Lm Chat Open Ai *Model*
- 8 **Prepare Research Context** Set *Logic*
- 9 **Agent A - Factual Research** Agent *Model*
- 10 **Agent B - Trends Research** Agent *Model*
- 11 **Agent C - Critical Research** Agent *Model*
- 12 **Critique Agent - Cross Validate** Agent *Model*
- 13 **Synthesis Agent - Generate Final Report** Agent *Model*
- 14 **Python - Validate & Decompose Topic** Code *Logic*
- 15 **JS - Aggregate Agent Outputs** Code *Logic*
- 16 **Python - Score & Rank Findings** Code *Logic*
- 17 **JS - Format Final Report** Code *Logic*
- 18 **Filter Valid Research Topics** Filter *Logic*
- 19 **Wait 1 - Agent Sync Buffer** Wait *Logic*
- 20 **Wait 2 - Critique Integration Buffer** Wait *Logic*
- 21 **Wait 3 - Final Review Buffer** Wait *Logic*
- 22 **Webhook Response - Deliver Report** Respond To Webhook *Starts it*
- 23 **Update Google Sheet Research Log** Http Request *Service*
- 24 **Email Report to Requester** Http Request *Service*

## How it's built

- **Starts on:** Another system calling it
- **Steps:** 24, 3 loops or waits
- **Size:** Large: read it before trusting it with anything live
- **Connects to:** Nothing by connector; it calls services over plain HTTP
- **Model:** OpenAI

## Questions

What does it need to run?

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

What starts it?

It starts on another system calling it.

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 24 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 24 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-multi-agent-ai-research-reports-with-openai)
- **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.

- [**AI model usage dashboard: Track token metrics** 24 steps · calls a model · n8n data table](https://millionrounds.com/workflow/ai-model-usage-dashboard-track-token-metrics)
- [**Analyze competitor Facebook ads with Gemini** 24 steps · calls a model · Gmail](https://millionrounds.com/workflow/analyze-competitor-facebook-ads-with-gemini)
- [**Automated multi-platform market intelligence reporting** 24 steps · calls a model · Gmail](https://millionrounds.com/workflow/automated-multi-platform-market-intelligence-reporting)
- [**Conversational Meta ads reporting & management with OpenAI** 24 steps · calls a model](https://millionrounds.com/workflow/conversational-meta-ads-reporting-and-management-with-openai)
- [**Customer insights with Qdrant and Python** 24 steps · calls a model · Google Sheets, Qdrant](https://millionrounds.com/workflow/customer-insights-with-qdrant-and-python)
- [**Generate AI-powered Strava performance evolution reports** 24 steps · calls a model · Gmail, Google Sheets](https://millionrounds.com/workflow/generate-ai-powered-strava-performance-evolution-reports)