Building close to the model, measuring what changed.

I'm studying a Bachelor of Information Technology at Macquarie University in Sydney, majoring in Artificial Intelligence. Most of what I build sits where language models meet real software: agents that take actions inside an organisation's tools, and full-stack products wrapped around them.

I care about measurement. It's easy to ship something that looks like it works — a demo, a fine-tune, a leaderboard number. It's harder to show what actually changed and what it cost. That gap is what pulls me toward LLM evaluation and reliability.

Outside that, I build and fly FPV drones, run, lift, and follow Formula 1 more closely than is strictly reasonable.