Generate and evaluate AI prompts with Gemini, OpenRouter, Groq, Cohere and Supabase
Ready for 3.0Ready for 3.0. This template uses no nodes that n8n 3.0 removes. No removed nodes, versions or helpers found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 14 nodes and runs when an HTTP POST request hits its webhook URL. Along the way it connects Google Gemini Chat Model, OpenRouter Chat Model, Groq Chat Model and Cohere Chat Model and 1 more.
How it runs
Trigger: When an HTTP POST request hits its webhook URL.
- Extract Goal (Code): runs custom JavaScript code
- Creative Prompt Agent (AI Agent): runs an AI agent, with model: Google Gemini Chat Model
- Marketing Prompt Agent (AI Agent): runs an AI agent, with model: OpenRouter Chat Model
- Technical Prompt Agent (AI Agent): runs an AI agent, with model: Groq Chat Model
- Merge: merges the data from its input branches
- Combine Agent Outputs (Code): runs custom JavaScript code
- Best Prompt Evaluator (AI Agent): runs an AI agent, with model: Cohere Chat Model
- Respond to Webhook: sends the response back to the webhook caller
- Create a row (Supabase): uses Supabase
Services it uses
Before you upgrade to n8n 3.0
Nothing in this workflow is removed in n8n 3.0, so it should import and run after the upgrade.
Rarely used nodes in this template: @n8n/n8n-nodes-langchain.lmChatCohere
Nodes used (10)
- Webhook
n8n-nodes-base.webhook - Google Gemini Chat Model
@n8n/n8n-nodes-langchain.lmChatGoogleGemini - OpenRouter Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenRouter - Groq Chat Model
@n8n/n8n-nodes-langchain.lmChatGroq - Cohere Chat Model
@n8n/n8n-nodes-langchain.lmChatCohere - Supabase
n8n-nodes-base.supabase - Merge
n8n-nodes-base.merge - Respond to Webhook
n8n-nodes-base.respondToWebhook - AI Agent
@n8n/n8n-nodes-langchain.agent - Code
n8n-nodes-base.code
From the author
Quick overview This workflow receives a goal via webhook, generates three prompt candidates using Google Gemini, OpenRouter, and Groq, has Cohere evaluate and select the best prompt, then returns the result to the caller and stores the goal and winning prompt…