You can’t prompt your way to better outcomes.
You have to build a system.
These guides are the operational layer of the Human–AI Loop methodology — the concrete setups, workflows, and practices that turn the ideas into something your team can actually run.
Pair them with the Human–AI Literacy Library for the frameworks and language to share with your team — then use these to make the work real.
📚 Core Playbooks
Six guides that walk you through building an AI collaboration practice from the ground up. Start with Guide 1 — everything else builds from it. Requires a paid AI plan (Claude Pro or ChatGPT Plus minimum) to run effectively.
Project Binder Setup
Set up AI collaboration context in 15 minutes. The foundation for everything else — without this, the other guides produce mediocre results.
Read Guide →Message Bus Protocol
Carry context between AI teammates. Master the human-as-message-bus pattern — the key to running a Triad without losing continuity.
Read Guide →Teach AI Your Voice
Help your AI match your communication style. Practical exercises and examples — the guide that makes everything else feel less like AI.
Read Guide →Identify AI Strengths and Roles
Assign tasks based on AI capabilities — divergence vs. synthesis, speed vs. rigor. The guide that makes the Triad model concrete for your specific work.
Read Guide →Organize Your Workspace
Build a simple, reliable system for projects, prompts, and context. Requires paid plans — Claude Projects and ChatGPT Projects are both paid features.
Read Guide →The 4 Moments That Taught Me
Stories from inside the loop that shaped how this methodology was built. The best emotional on-ramp for skeptics — start here if you’re not sure this is for you.
Read Guide →📖 Human–AI Literacy Library
Short, visual explainers and frameworks for the concepts you need to collaborate with AI inside real work. Core episodes cover how AI behaves. Infopanels and comparisons show how to design the collaboration system itself.
Core Literacy Episodes — How AI Behaves
Foundational concepts: how models predict, drift, forget, and sometimes generate confident nonsense — and how to work with that reality without losing human judgment.
Why AI Hallucinates
What hallucinations are (and aren’t), where they come from, how to spot them, and how to design workflows around them.
View panel →Anthropomorphism Isn’t the Problem
Why modern AI feels human, and how treating it like a teammate improves the work when humans stay accountable for vision and judgment.
View panel →When AI “Forgets”
Catastrophic forgetting vs. conversation-time drift — and how to work with models that lose the thread without losing your mind.
View panel →Which Model Is My AI Tool Using?
A practical guide to which underlying model powers your tools, why it matters, and how to ask better questions about risk and capability.
View panel →Infopanels & Comparative Frameworks — Collaboration Design
Practical models you can reuse with teams: tradeoffs, trust boundaries, feedback loops, and decision ownership. This is where “AI as a teammate” becomes a designable collaboration system — not a slogan.
Impostor Syndrome & AI Hallucinations
A side-by-side look at human self-doubt and machine overconfidence — and why collaboration is the real winning hand.
View panel →Not All AI Should Be Your Teammate
How to tell the difference between AI you should treat as a collaborator and AI that’s best used as a tool with clear boundaries.
View panel →Five Principles of Human–AI Collaboration
The non-negotiables for treating AI as a true teammate — keeping humans at the center while AI accelerates the work around us.
View panel →Inside The Human/AI Triad
One human, two AI teammates — a concrete way to design roles, rhythm, and shared context for collaboration.
View panel →Inside The Collaboration Loop
A simple model for leading real work with AI partners — from brief, to exploration, to alignment, to decisions you can stand behind.
View panel →Prompt Engineering vs Collaboration Engineering
When AI is a tool vs a teammate — and how to design collaboration patterns, not just clever prompts.
View panel →Building the Plane vs Rebuilding the Cockpit
Teams adopt AI while still shipping. This comparison shows why augmentation is a collaboration design problem — context systems, trust boundaries, decision ownership — not just a tooling rollout.
Read / view →🎯 Tools in Action
The playbooks teach the methodology. The literacy panels explain the concepts. These tools show what it looks like when you build real apps with the Triad model.
📘 Platform-Specific Guides
Quick reference guides and setup instructions for working with specific AI platforms. Use these alongside the core playbooks to keep your system grounded.
📘 Universal Guides
Applicable across all AI platforms.
🎙️ ChatGPT-Specific
Setup and workflows for ChatGPT / CP.
🤖 Claude-Specific
Setup and workflows for Claude / Soph. In progress.
🔮 More Coming Soon
We’re adding more guides based on real project learnings:
- → Advanced context management
- → Multi-thread project coordination
- → Team collaboration patterns
- → Quality assurance workflows
The philosophy behind this work
“We’re less interested in what AI can produce — and more interested in what humans and AI can achieve together.”
That’s not a tagline. It’s the question that drives every framework, playbook, and experiment in this ecosystem — and the one the Human–AI Loop methodology exists to answer.
Methodology
Guides & Playbooks
Literacy & Writing
Tools & Connect
aigal.io 