AutomationMart
Home/Browse/Evaluate tool usage accuracy in multi-agent AI workflows using evaluation nodes
n8n

Evaluate tool usage accuracy in multi-agent AI workflows using evaluation nodes

n8nn8n15 modulesv1.0
Google SheetsOpenAI

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 expectations, this workflow gives you plug-and-play observability. What it does ------------ This template uses n8n's built-in Evaluation Trigger and Evaluation nodes to assess whether an AI agent correctly used all the expected tools. It suppor

At a glance

Evaluate tool usage accuracy in multi-agent AI workflows using evaluation nodes is a ready-made n8n workflow you import as a workflow JSON file — no build required. It connects Google Sheets, OpenAI. It's free to download. Follow the 5-step import below to go live in minutes.

Platform
n8n
Connects
Google Sheets, OpenAI
Modules
15
Price
Free
Version
v1.0
Evaluate tool usage accuracy in multi-agent AI workflows using evaluation nodes workflow diagram

About this workflow

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 expectations, this workflow gives you plug-and-play observability. What it does ------------ This template uses n8n's built-in Evaluation Trigger and Evaluation nodes to assess whether an AI agent correctly used all the expected tools. It supports: - Dataset-driven testing of agent behavior - Logging actual tools to compare them with the expected tools - Assigning performance metrics (toolcalled = true/false) - Persisting output back to Google Sheets for further debugging The workflow can be triggered by either the chat input or the dataset row evaluation. It routes through a multi-tool agent node powered by the best LLMs. The agent has access to tools such as web search, calculator, vector search, and summarizer tools. The workflow then aims to validate tool use decisions by extracting the intermediate steps from the agent (i.e., action + observation) and comparing the tools that were called with the expected tools. If the tools that were called during the workflow execution match, then it's a pass; otherwise, it's documented as a fail. The evaluation nodes take care of that process.  How to set it up ---------------- 1. Connect your Google Sheets OAuth2 credential. Replace the document with your own test dataset. 2. Set your desired models and configure the different agent tools, such as the summarizer and vector store. The default vector store used is Qdrant, so the user must create this vector store with a few samples of queries + web search results. 3. Run from either the chat trigger or the evaluation trigger to test. Requirements ------------ - Google Sheets OAuth2 credential - OpenRouter / OpenAI credentials for AI agents and embeddings - Firecrawl and Qdrant credentials for web + vector search How to customize ---------------- - Edit the Search Agent system message to define tool selection behavior - Add more metric columns in the Evaluation node for complex scoring - Add new tool nodes and link them to the agent block - Swap in your own summarizer

n8n

How to import this n8n workflow

  1. 1

    Download the workflow JSON file after purchase.

  2. 2

    Open n8n → click the menu → Import from File.

  3. 3

    Select the downloaded JSON and import.

  4. 4

    Set up credentials for each node that requires them.

  5. 5

    Click Execute Workflow to test, then activate.

Setup guide

Setup guide included

Purchase to unlock the full step-by-step guide

Related N8n workflows

Create Freshsales leads from new rows on a Google Sheets spreadsheet

Every time you add a new row to your Google Sheets spreadsheet, Make will automatically create a new lead in Freshsales. The template uses this [example spreadsheet](http://bit.ly/2LaFWYo).

Free

Add new Monday.com group items as rows in Google Sheets

Streamline your project management by automatically tracking updates in Monday.com and logging them in Google Sheets. With this template, every time a new item is added to a specified group in Monday.com, Make will seamlessly create a new row in your Google Sheets. This ensures that you have a real-time record of your project progress, making it easier to analyze and manage your tasks effectively. Perfect for teams looking to enhance their workflow and maintain organized documentation.

Free

Automate SEO blog post creation and publishing with OpenAI & WordPress

AI WordPress - SEO Content Generator automates creating and publishing SEO-friendly blog articles on WordPress. It combines AI technologies like OpenAI and OpenRouter to craft catchy titles, write 1500+ word articles, generate natural featured images, and publish everything seamlessly. This workflow turns your WordPress site into a content powerhouse that boosts traffic and saves you hours by handling the entire blog post process automatically. Why Use AI WordPress - SEO Content Generator? Save

Free

Track SEO keyword rankings in Google Search with ScrapingBee API

Who is this template for? This SEO Reporting workflow template is ideal for digital marketers, SEO consultants, content strategists, and founders who need to quickly gather, format, and store Google search result data. If you regularly audit SERPs, track keyword performance, or monitor competitors, this automation lets you generate polished SEO reports in seconds—ready to share or analyze further. What problem does this workflow solve? Scraping and formatting Google search results for SEO insigh

Free

Automated proof-of-delivery with GPT-4 Vision & ERP/Invoice integration

This n8n workflow automates the end-to-end proof-of-delivery process for logistics operations. It ingests POD data via webhook—including driver signatures, delivery photos, and GPS coordinates—performs AI-driven verification for package integrity and authenticity, updates ERP systems with delivery status, triggers automated invoicing for verified cases, and handles disputes by creating evidence-backed tickets and alerting teams. Designed for seamless integration, it minimizes errors in billing a

Free

Stock market technical analysis with GPT-4o and TradingView for Telegram

Overview: Transform Your Trading with AI-Driven Technical Analysis The Stock Market Technical Analysis Bot is an advanced n8n workflow that brings professional-grade stock analysis to Telegram users. This powerful AI agent analyzes stock charts in real-time, providing detailed technical insights that would typically require expensive software or expert knowledge. By combining artificial intelligence with technical analysis indicators, this bot delivers actionable trading insights directly to you

Free

Email assistant: convert natural language to SQL queries with Phi4-mini and PostgreSQL

Who is this for? 🧑🏻🫱🏻‍🫲🏻🤖 Humans and Robots alike. This workflow can be used as a Chat Trigger, as well as a Workflow Trigger. It will take a natural language request, and then generate a SQL query. The resulting query parameter will contain the query, and a sqloutput parameter will contain the results of executing such query. What's the use case? This template is most useful paired with other workflows that extract e-mail information and store it in a structured Postgres table, and use LLMs to

Free

Scrape & import shoe products to Shopify with BrowserAct (with variants & images)

Scrape & Import Products to Shopify from Any Site (with Variants & Images)-(Optimized for shoes) This advanced n8n template automates e-commerce operations by scraping product data (including variants and images) from any URL and creating fully detailed products in your Shopify store. This workflow is essential for dropshippers, e-commerce store owners, and anyone looking to quickly import product catalogs from specific websites into their Shopify store. --- Self-Hosted Only This Workflow uses

Free

Reviews

No reviews yet

Be the first to buy and share your experience.

Leave a review

Sign in to share your experience with this workflow.

Log in to review
Free
No ratings yet

Create a free account to purchase workflows.

  • JSON blueprint — instant download
  • Setup guide PDF included
  • 5 downloads · valid 30 days
  • Works with n8n

Need help setting this up?

Book a 3-hour live setup session with an Agility consultant.

₹2,499/ session
3 hrs · video call
  • Configure live on Google Meet / Zoom
  • Free follow-up if workflow has defects
  • Platform expert assigned to you
Book installation session
Free