
From ChatGPT to Agents: The Next Human–AI Collaboration Model
Moving from question-answering models to agents that can plan, use tools, execute work, and verify outcomes.
Field notes on AI systems, agents, and building useful software.

Moving from question-answering models to agents that can plan, use tools, execute work, and verify outcomes.
The motivation, principles, and next steps behind DogXAI—and a commitment to building a more open world.
Turning scattered Markdown, project notes, and research into a searchable, versioned knowledge system that can evolve over time.
Retrieval, chunking, reranking, and evaluation—the engineering work required to move RAG from demo to production.
The small set of tools and habits I use to shorten the distance between thinking and shipping.
A practical method for turning an idea into a product that can actually be used.
Smaller teams and individuals can build with far more leverage—but judgment matters more than ever.