# Evaluate tool usage accuracy in multi-agent AI workflows: n8n workflow

> Started by someone opening a chat with it, and works across Qdrant. It puts OpenAI and OpenRouter behind a retrieval step, so answers are drawn from...

Source: https://millionrounds.com/workflow/evaluate-tool-usage-accuracy-in-multi-agent-ai-workflows (Millionrounds; every figure on the page links to its filing or article)

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

# Evaluate tool usage accuracy in multi-agent AI workflows

Started by someone opening a chat with it, and works across Qdrant. It puts OpenAI and OpenRouter behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 15 steps: a working afternoon to understand properly.

Medium Calls a model: OpenAI, OpenRouter Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fevaluate-tool-usage-accuracy-in-multi-agent-ai-workflows)

**15 steps** Medium: a working afternoon

**0** Branches: places the flow splits

**0** Loops or waits

**1** Service it connects to

## The flow

Starts it 2 Model 6 Logic 3 Service 4

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

- 1 **Calculator** Tool Calculator *Model*
- 2 **When chat message received** Chat trigger *Starts it*
- 3 **When fetching a dataset row** Evaluation trigger *Starts it*
- 4 **Summarizer** Tool Workflow *Model*
- 5 **Web search** Http Request Tool *Service*
- 6 **OpenRouter Chat Model** Lm Chat Open Router *Model*
- 7 **Embeddings OpenAI** Embeddings Open Ai *Model*
- 8 **Search Agent** Agent *Model*
- 9 **Match chat format** Set *Logic*
- 10 **Search_db** Vector Store Qdrant *Model*
- 11 **Evaluating?** Evaluation *Service*
- 12 **Check if tool called** Set *Logic*
- 13 **Return chat response** No Op *Logic*
- 14 **Set Outputs** Evaluation *Service*
- 15 **Evaluation** Evaluation *Service*

## How it's built

- **Starts on:** Someone opening a chat with it
- **Steps:** 15
- **Size:** Medium: a working afternoon
- **Connects to:** Qdrant
- **Model:** OpenAI, OpenRouter
- **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 Qdrant account, and a key for OpenAI and OpenRouter. 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 OpenAI and OpenRouter. 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. 15 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 15 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%2Fevaluate-tool-usage-accuracy-in-multi-agent-ai-workflows)
- **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.

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

## Workflows like it

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

- [**Chat with Gemini and Qdrant** 15 steps · calls a model · Qdrant](https://millionrounds.com/workflow/chat-with-gemini-and-qdrant)
- [**Convert DevOps Mattermost requests into Jira tasks** 15 steps · calls a model · Jira, Mattermost](https://millionrounds.com/workflow/convert-devops-mattermost-requests-into-jira-tasks)
- [**Bulletproof RAG starter – Google Drive to chatbot with OpenAI** 16 steps · calls a model · Google Drive, Qdrant](https://millionrounds.com/workflow/bulletproof-rag-starter-google-drive-to-chatbot-with-openai)
- [**Build persistent chat memory with OpenAI and Qdrant** 13 steps · calls a model · Qdrant](https://millionrounds.com/workflow/build-persistent-chat-memory-with-openai-and-qdrant)
- [**AI email autoresponder with OpenAI and Gmail** 12 steps · calls a model · Email, Gmail](https://millionrounds.com/workflow/ai-email-autoresponder-with-openai-and-gmail)
- [**AI-powered email processing autoresponder** 12 steps · calls a model · Email, Gmail](https://millionrounds.com/workflow/ai-powered-email-processing-autoresponder-2)