Your 9-Step Journey to Thinking With AI

Freestyle Cognition is a hands-on system for using AI as a creative partner. This site will guide you—step by step—through everything you need to get started.

Begin the Journey
Step 1
Start With a Visual Walkthrough

Watch the slides to understand what Freestyle Cognition is and how it works.

▶️ View
Step 2
Try Prompt Examples

See how prompts shape the conversation and guide the AI’s response.

💬 Try
Step 3
Learn Prompt Techniques

Explore frameworks like GROW and ALIGN that guide better interaction.

🔧 Learn
Step 4
Combine Prompt Templates

Use the builder to chain techniques together for powerful results.

🧰 Build
Step 5
Explore the Toolkit

Interact with mini apps that wrap prompts into usable tools.

🛠 Open
Step 6
Read the Book

Dive into the complete Freestyle Cognition system in structured form.

📖 Read
Step 7
Explore Real Sessions

See how the system works in practice—real prompts, real outcomes.

📘 View
Step 8
See the Prompt Slides

Visual slideshows of each template, technique, and system loop.

🖼 Slides
Step 9
Join the Creative Loop

Apply what you’ve learned and start building with AI today.

🚀 Join

📰 Latest Insights

Freestyle Cognition

🧠 Freestyle Cognition: A New Way of Thinking and Building with AI

Posted by Ernan Hughes Author of Freestyle Cognition


“You’ve probably already felt it. You gave the AI a messy thought… and it came back with something better. That little magic moment? That’s Freestyle Cognition.”


What Is Freestyle Cognition?

Freestyle Cognition is not just another AI prompt strategy. It’s a process — a new way to think with AI, not just ask it for help.

Read More
Programming Intelligence: Using Symbolic Rules to Steer and Evolve AI

🧪 Summary

“What if AI systems could learn how to improve themselves not just at the level of weights or prompts, but at the level of strategy itself? In this post, we show how to build such a system, powered by symbolic rules and reflection.

The paper Symbolic Agents: Symbolic Learning Enables Self-Evolving Agents introduces a framework where symbolic rules guide, evaluate, and evolve agent behavior.

Read More
Adaptive Reasoning with ARM: Teaching AI the Right Way to Think

Summary

Chain-of-thought is powerful, but which chain? Short explanations work for easy tasks, long reflections help on hard ones, and code sometimes beats them both. What if your model could adaptively pick the best strategy, per task, and improve as it learns?

The Adaptive Reasoning Model (ARM) is a framework for teaching language models how to choose the right reasoning format direct answers, chain-of-thoughts, or code depending on the task. It works by evaluating responses, scoring them based on rarity, conciseness, and difficulty alignment, and then updating model behavior over time.

Read More
A Novel Approach to Autonomous Research: Implementing NOVELSEEK with Modular AI Agents

Summary

AI research tools today are often narrow: one generates summaries, another ranks models, a third suggests ideas. But real scientific discovery isn’t a single step—it’s a pipeline. It’s iterative, structured, and full of feedback loops.

In this post, I show how to build a modular AI system that mirrors this full research lifecycle. From initial idea generation to method planning, each phase is handled by a specialized agent working in concert.

Read More
The Self-Aware Pipeline: Empowering AI to Choose Its Own Path to the Goal

🔧 Summary

Modern AI systems require more than just raw processing power they need contextual awareness, strategic foresight, and adaptive learning capabilities. In this post, we walk through how we implemented a self-aware pipeline system inspired by the Devil’s Advocate paper.

Unlike brittle, static workflows, this architecture empowers agents to reflect on their own steps, predict failure modes, and adapt their strategies in real time.


🧠 Grounding in Research

Devil’s Advocate (ReReST)

ReReST: Devil's Advocate: Anticipatory Reflection for LLM Agents introduces a self-training framework for LLM agents. The core idea is to have a “reflector” agent anticipate failures and revise the original plan before executing a powerful method for reducing hallucinations and improving sample quality. Our implementation draws heavily on these ideas to enable dynamic planning and feedback loops within the pipeline.

Read More
General Reasoner: The smarter Local Agent

🔧 Summary

The General Reasoner paper shows how we can train LLMs to reason across domains using diverse data and a generative verifier. In this post, I walk through our open-source implementation showing how we built a modular reasoning agent capable of generating multiple hypotheses, evaluating them with an LLM-based judge, and selecting the best answer.


🧠 What We Built

We built a GeneralReasonerAgent that:

  • Dynamically generates multiple hypotheses using different reasoning strategies (e.g., cot, debate, verify_then_answer, etc.)
  • Evaluates each pair of hypotheses using either a local LLM judge or our custom MR.Q evaluator
  • Classifies the winning hypothesis using rubric dimensions
  • Logs structured results to a PostgreSQL-backed system

All of this was integrated with our existing co_ai framework, which includes:

Read More

About the Author

Ernan Hughes writes at the frontier of human-machine collaboration, building frameworks that help people think, create, and live more powerfully with AI.

Frequently Asked Questions

Freestyle Cognition is a new way of working with AI — not just asking it for help, but collaborating as cognitive partners to build, think, and create at higher levels.

No! This book is designed for anyone — writers, entrepreneurs, researchers, students — anyone curious about using AI to expand their abilities.

A phone or computer that can connect to the internet.

Anyone ready to unlock deeper interaction with AI writers, builders, solopreneurs, knowledge workers, and thinkers.

Ready to Amplify Your Thinking?

Get the Book