Evaluate tool usage accuracy in multi-agent AI workflows using evaluation nodes
Needs changesNeeds changes. This template uses 1 thing(s) that n8n 3.0 removes: AI Agent v1 (old agent modes). 1 breaking item(s) found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 15 nodes and runs on Evaluation events (plus 1 other trigger). Along the way it connects Evaluation, HTTP Request, OpenRouter Chat Model and Embeddings OpenAI and 1 more. It also calls api.firecrawl.dev over HTTP.
How it runs
Trigger: On Evaluation events (plus 1 other trigger).
- Match chat format (Edit Fields (Set)): sets 1 field: chatInput
- Search Agent (AI Agent): runs an AI agent, with model: OpenRouter Chat Model; 4 tools (Search_db, Calculator, Summarizer, Web search)
- Evaluating? (Evaluation): check if evaluating
- Check if tool called (Edit Fields (Set)): sets 1 field: tool_called
- Set Outputs (Evaluation): uses Evaluation
- Evaluation: set metrics
Services it uses
HTTP calls to: api.firecrawl.dev
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- AI Agent v1 (old agent modes) in Search Agent (v1.9): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) Search Agent (v1.9) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (12)
- Calculator
@n8n/n8n-nodes-langchain.toolCalculator - Edit Fields (Set)
n8n-nodes-base.set - Chat Trigger
@n8n/n8n-nodes-langchain.chatTrigger - No Operation, do nothing
n8n-nodes-base.noOp - Evaluation Trigger
n8n-nodes-base.evaluationTrigger - Evaluation
n8n-nodes-base.evaluation - AI Agent
@n8n/n8n-nodes-langchain.agent - Call n8n Workflow Tool
@n8n/n8n-nodes-langchain.toolWorkflow - Http Request Tool
n8n-nodes-base.httpRequestTool - OpenRouter Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenRouter - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - Qdrant Vector Store
@n8n/n8n-nodes-langchain.vectorStoreQdrant
From the author
Who's it for ------------ This workflow is ideal for AI developers running multi-agent systems in n8n who need to quantitatively evaluate tool usage behavior. If you're building autonomous agents and want to verify their decisions against ground-truth…