I'm an author, hands-on builder, and AI Craft leader from New Zealand. I use Codex and other AI tools to turn ambitious ideas into working projects, then study what makes AI-assisted software development useful, reliable, and easy to understand.

I publish plain-English guides and small runnable examples for reliable AI agents, local AI assistants, human-reviewed workflows, source boundaries, scoped authority, and verification evidence. Most examples use synthetic data and run without calling a model.

I'm especially interested in helping people who do not identify as programmers direct serious builds without giving up control of the decisions that matter.

• Want a useful first project now? Create a private Reliable AI Work Starter for one recurring workflow with named sources, approval boundaries, durable state, and a reviewable handoff. It needs no app, model API, or public data.
• New to building with AI? Start with Build with Codex: A Plain-English Handbook to turn an idea into a bounded project and review the result without needing to read all the code.
• Reviewing AI-assisted code? Try EvidenceGate, a practical way to bind claims, checks, file scope, and human review to one Git revision.
• Designing a reliable AI agent? The Toolkit Navigator connects source boundaries, scoped authority, focused checks, and a replayable receipt in one synthetic workflow, then recommends a public pattern by problem, experience, runtime, proof, and limitation.
• Building a game with Codex? Use the Game Project Instructions for Coding Agents to protect assets and saves, define approval gates, choose exact checks, and preserve the human playtest. It is adaptable to Godot, Unity, Unreal, or a custom engine.

• Reviewable agent work. Context Boundary Examples catches answers that outrun supplied evidence, while Agent Action Authority Examples tests whether an approval still matches the exact action being proposed.
• Local-first assistant reliability. The Local Model Reliability Example keeps structured model output behind deterministic validation, and the SQLite Context Retrieval Example shows how small metadata rules prevent specific retrieval failures.
• Repeatable project confidence. The Green-Spine QA Pattern turns a representative end-to-end journey into one memorable checkpoint, while the Public Repo Safety Kit helps keep private context out of public repositories.

These projects favour small synthetic examples, explicit limitations, and evidence a reviewer can inspect. A passing check is useful evidence, not a claim that the work is automatically correct, safe, or ready to publish.

Use the Lab's two-minute Toolkit Navigator to get one recommendation, or scan the complete toolkit map when you want every option and trust boundary at once.

I keep the broader lessons in Field Notes From Building With AI: what the surrounding harness should own, why useful work and permitted work are different, how to test boundaries before calling a model, and where human judgement still has to decide the outcome.

Away from the technical work, I write stories where fantasy, science fiction, and the apocalypse collide. I'm the author of The Mana Influx Series and Soul Spark Reclaimer. You can meet The Mana Influx Series on Amazon.

• Make capability accessible. People should be able to direct ambitious projects in ordinary language and understand the important decisions.
• Keep humans responsible. Models can propose and produce; people retain authority over consequential actions and protected areas.
• Leave something inspectable. Useful AI-assisted work has clear limits, relevant checks, honest uncertainty, and a handoff another person can review.

I like making real things, learning from where they break, and sharing the smallest useful version with other people.