Generate Collaborative Handbooks with GPT-4o Multi-Agent Orchestration & Human Review

AI-Driven Handbook Generator with Multi-Agent Orchestration (Pyragogy)

Description:

This n8n workflow implements a modular multi-agent AI orchestration system for the collaborative generation of Markdown-based handbooks.
Inspired by peer learning and open publishing workflows, it simulates a content pipeline where AI agents (e.g. Summarizer, Synthesizer, Sensemaking Agent, Peer Reviewer) act in well-defined roles — enabling true AI–human co-creation and iterative refinement.

This project is part of Pyragogy — an open framework dedicated to ethical cognitive co-creation, peer AI–human learning, and human-in-the-loop automation for open knowledge systems.

⚙️ How it works

• A Webhook Trigger receives user input (e.g. “Write a chapter on community-based learning”).
• A Meta-Orchestrator (via GPT-4o) analyzes the request and activates the right combination of AI agents.
• Tasks are dynamically routed and assigned based on each agent’s responsibility.
• Each agent executes its step (summarizing, synthesizing, reviewing...) using OpenAI or custom endpoints.
• A Peer Review Board of AI agents evaluates the output. If issues are flagged, it triggers redrafting loops via the Synthesizer.
• Clean, structured output is returned as Markdown with YAML frontmatter or raw JSON.
• Optionally, a human reviewer (HITL) can approve, reject, or comment via webhook.
• Approved content is saved to PostgreSQL, pushed to GitHub, or synced with Notion/Obsidian.

🛠 Setup Steps

1. Import the pyragogy_master_workflow.json into your n8n instance.
2. Connect your OpenAI credentials (GPT-4o suggested).
3. Define essential environment variables (.env.template included in the repo) — e.g. API base, database, GitHub, email.
4. (Optional) Configure PostgreSQL and GitHub for content persistence and versioning.

Send a sample payload to your webhook URL:(/webhook/pyragogy/process):

{
  "title": "History of Peer Learning",
  "text": "Peer learning is an educational approach where students learn from and with each other...",
  "tags": ["education", "pedagogy"],
  "requireHitl": true
}

Observe the dynamic loop:
orchestrate → assign → generate → review (AI/human) → store

📚 Full documentation, contribution guidelines, and API structure available here:
🔗 GitHub – pyragogy-handbook-n8n-workflow

🧠 Ideal for:

• Educators exploring AI-assisted publishing
• Knowledge teams automating content pipelines
• Researchers co-authoring with AI
• Anyone building collaborative markdown-driven tools

🔁 This workflow is open-source and community-driven.
We warmly invite you to improve it, remix it, adapt it to your use case — and share it back.