Make multi-agent council decisions with OpenAI GPT-5

by Cheng Siong Chin ✓ · 189 views · created 2026-06-07 · Engineering, AI Chatbot

What this workflow does

This AI workflow has 16 nodes and runs manually, when you click “Execute workflow”. Along the way it connects OpenAI Chat Model.

How it runs

Trigger: Manually, when you click “Execute workflow”.

1. Prepare Proposal (Edit Fields (Set)): sets 2 fields: proposal, context
2. Strategic Thinker Agent (AI Agent): runs an AI agent, with model: OpenAI GPT-; output parser: Strategist Output Parser
3. Contrarian Thinker Agent (AI Agent): runs an AI agent, with model: OpenAI GPT-; output parser: Contrarian Output Parser
4. Ethics & Compliance Agent (AI Agent): runs an AI agent, with model: OpenAI GPT-; output parser: Ethics Output Parser
5. Execution & Operations Agent (AI Agent): runs an AI agent, with model: OpenAI GPT-; output parser: Execution Output Parser
6. Aggregate: combines items into one
7. Prepare Chairman Input (Edit Fields (Set)): sets 4 fields: originalProposal, context, agentPerspectives…
8. Chairman Agent (AI Agent): runs an AI agent, with model: OpenAI GPT-; output parser: Chairman Output Parser
9. Format Council Decision (Edit Fields (Set)): sets 6 fields: proposal, decision, summary…

Services it uses

OpenAI Chat Model

Before you upgrade to n8n 3.0

Nodes used (6)

• Manual Triggern8n-nodes-base.manualTrigger
• Edit Fields (Set)n8n-nodes-base.set
• AI Agent@n8n/n8n-nodes-langchain.agent
• OpenAI Chat Model@n8n/n8n-nodes-langchain.lmChatOpenAi
• Structured Output Parser@n8n/n8n-nodes-langchain.outputParserStructured
• Aggregaten8n-nodes-base.aggregate

From the author

Quick Overview This workflow runs a manual “AI council” that evaluates a proposal with four OpenAI-powered specialist agents, aggregates their structured perspectives, and has a chairman agent synthesize a final decision with voting, rationale, and action…

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