Course — coming soon

Ship With AI

A course for engineers who want to stop guessing and start building.

I've spent 10 years building AI products. Before ChatGPT. Before agents. Before any of this was cool.

This course is everything I wish someone had handed me on day one.

Join the waitlist
I'll let you know when it's ready.

Most engineers are using AI wrong

Not because they're bad engineers. Because the information out there is a mess.

Half of it is hype from people who've never shipped a product. The other half is documentation that assumes you already know what you're doing.

There's no clear path from “I've heard of Claude Code” to “I just built and deployed a full product in a weekend.”

I know because I've been on both sides. I've built AI systems that serve millions of candidates for the world's biggest recruitment companies. And I've also sat in front of a blinking cursor not knowing where to start.

The gap isn't talent. It's having someone show you how the pieces actually fit together.

What the course covers

This isn't a tutorial playlist. It's a structured path from understanding how LLMs actually work to shipping production AI products.

  1. Part 1

    How LLMs actually work

    Not the PhD version. The version that matters when you're building products. What's really happening when you send a prompt. Why some approaches work and others waste tokens and time. The mental models that change how you think about every AI interaction.

  2. Part 2

    Thinking like an AI product engineer

    How to evaluate what AI should and shouldn't do in your product. Prompt architecture that holds up in production, not just in a playground. Patterns from building conversation engines used by Brunel, Robert Walters, and some of the biggest recruitment enterprises in the world.

  3. Part 3

    AI tools for everyday work

    The desktop and web tools that actually save time. Not a feature tour. The specific workflows I use daily that most people don't know exist.

  4. Part 4

    Shipping with AI coding agents

    Claude Code. Cursor. Codex. What they share, where they differ, and when to use which. You'll learn the shared language across all of them so you're not starting from scratch every time a new tool drops.

  5. Part 5

    The full picture

    Where it all comes together. How I work as an AI product engineer at a startup, running my own company, and shipping side projects. The systems, the shortcuts, the tradeoffs nobody talks about.

This is for you if…

You're an engineer who knows AI matters but feels overwhelmed by the noise. You've tried a few tools, maybe followed some tutorials, but nothing clicked into a real workflow.

Or you're earlier than that. You've been coding for a while but haven't really touched AI tooling yet. You know you need to, but the landscape moves so fast you don't know where to start.

Or maybe you're already using Cursor or Claude Code but you know you're only scratching the surface. You want the full playbook.

This is not for complete beginners to programming. You should be comfortable writing code. Everything else, I'll teach you.

Why me

I've been building AI products since before the current wave. My career path through AI:

Arria NLG
Built one of the first pre-LLM natural language generation systems. We were making AI write before GPT existed. Including one of the first pluralisation classifiers.
Cub Digital
Co-founded and built AI solutions for the All Blacks, Air New Zealand, and the NZ Stock Exchange.
Popp AI
Senior Engineer building the conversation engine that powers recruitment for some of the world's largest enterprises. Millions of candidate interactions. Real production AI at scale.

I also write about this stuff constantly. 1.8M+ views on Medium. Articles on Claude Code, AI agents, and developer workflows that regularly hit thousands of readers. I'm not a course creator who picked up AI last year. This is what I do every day.

Join the waitlist

The course is in development right now. Drop your email and I'll let you know when it launches. No spam. No “weekly updates about nothing.” Just a heads up when it's ready.

I'm building this because people kept asking for it. If that's you, I want to make sure you hear about it first.

Questions

When does it launch?
Soon. I'm building it alongside my actual work, not outsourcing it to a content farm. That means it takes a bit longer, but everything in it comes from real experience.
How much will it cost?
Haven't set the final price yet. Waitlist members will get early access pricing.
Is this just for TypeScript/Next.js developers?
No. The AI mental models and workflows apply regardless of your stack. The coding agent sections lean TypeScript because that's what I ship in daily, but the principles transfer.
Will there be a community?
Potentially. I want to get the course right first. Community might come later if there's demand.