Automate LLM testing with GPT-4 judge & Google Sheets tracking

by Adam Janes ✓ · 1,109 views · created 2025-07-16 · Engineering, AI Summarization

What this workflow does

This AI workflow has 12 nodes and runs manually, when you click “Execute workflow” (plus 1 other trigger). Along the way it connects Google Sheets and OpenRouter Chat Model. It also calls webhook-processor-production-48f8.up.railway.app over HTTP.

How it runs

Trigger: Manually, when you click “Execute workflow” (plus 1 other trigger).

1. Get Tests (Google Sheets): uses Google Sheets
2. Keep Original Data (Edit Fields (Set)): sets or maps fields
3. Extract Data (Edit Fields (Set)): sets or maps fields
4. Limit: keeps the first few items
5. Merge: merges the data from its input branches
6. Basic LLM Chain: sends a prompt to an LLM, with model: OpenRouter Chat Model; output parser: Structured Output Parser
7. Execute Subworkflow (HTTP Request): calls webhook-processor-production-48f8.up.railway.app (POST)
8. Update Results (Google Sheets): append or update

Services it uses

Google SheetsOpenRouter Chat Model

HTTP calls to: webhook-processor-production-48f8.up.railway.app

Before you upgrade to n8n 3.0

Nodes used (10)

• Mergen8n-nodes-base.merge
• Structured Output Parser@n8n/n8n-nodes-langchain.outputParserStructured
• Google Sheetsn8n-nodes-base.googleSheets
• Limitn8n-nodes-base.limit
• Edit Fields (Set)n8n-nodes-base.set
• HTTP Requestn8n-nodes-base.httpRequest
• Webhookn8n-nodes-base.webhook
• Basic LLM Chain@n8n/n8n-nodes-langchain.chainLlm
• OpenRouter Chat Model@n8n/n8n-nodes-langchain.lmChatOpenRouter
• Manual Triggern8n-nodes-base.manualTrigger

From the author

How it works - The workflow loads a list of test cases from a Google Sheet (previous results stored from an LLM) - For each test case, we execute a call to an LLM judge in parallel (using HTTP Request + Webhook nodes) - The judge uses the Input, Output, and…

View the original on n8n.io → Check your own copy