Stress-test decisions and compare plans with Gemini and Claude
Ready for 3.0What this workflow does
This AI workflow has 14 nodes and runs when someone submits an n8n form (“Second opinion”) (plus 1 other trigger). Along the way it connects Google Gemini Chat Model and Anthropic Chat Model.
How it runs
Trigger: When someone submits an n8n form (“Second opinion”) (plus 1 other trigger).
- Normalize and Quote Input (Code): runs custom JavaScript code
- Conduct Devil's Advocate Review (Basic LLM Chain): sends a prompt to an LLM, with model: Gemini Devil's Advocate Model; output parser: Parse Plan B Output
- Create Synthesis Prompt (Code): runs custom JavaScript code
- Evaluate and Recommend Plans (Basic LLM Chain): sends a prompt to an LLM, with model: Claude Synthesis Model; output parser: Parse Recommendation Output
- Verify and Format Final Result (Code): runs custom JavaScript code
- Check Form Source (If): checks a condition and branches into true / false
- Display Result in Form (n8n Form): shows the next form page
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.
Nodes used (10)
- n8n Form Trigger
n8n-nodes-base.formTrigger - Execute Workflow Trigger
n8n-nodes-base.executeWorkflowTrigger - Code
n8n-nodes-base.code - Basic LLM Chain
@n8n/n8n-nodes-langchain.chainLlm - Google Gemini Chat Model
@n8n/n8n-nodes-langchain.lmChatGoogleGemini - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - Anthropic Chat Model
@n8n/n8n-nodes-langchain.lmChatAnthropic - If
n8n-nodes-base.if - n8n Form
n8n-nodes-base.form - No Operation, do nothing
n8n-nodes-base.noOp
From the author
Quick overview Get an honest second opinion on a plan or decision before you act. Gemini plays devil's advocate and proposes a Plan B, Claude weighs both and recommends A, B or a mix. Works as a form or as a sub-workflow for AI agents. How it works 1. Input…