With the current rate of AI progress, every AI product builder must confront an uncomfortable question: How should I build my product when my approach could become obsolete with the next model rele...

A popular maxim when building LLM products is to “look at your data”: one of the best ways to understand and improve AI performance is to review your AI outputs. But what if you can’t understand y...

This is a lightning lesson with Jason Liu delivered on 13th August 2025. Recording Slides Downloadable as a PDF here.

This is a guest lecture as part of the AI Evals For Engineers & PMs online course (7th August 2025). Recording (Will be uploaded later - sign up below to be notified.) Slides Download...

Without human reviews of AI outputs from your product, you’re flying blind. You don’t truly know how your app is performing nor how you could improve it. Performance could drop and you won’t know u...

It’s a common scenario: you’ve got an entrepreneurial itch, an idea you’re really excited to build… it’s just, you don’t really know how to build it. Perhaps you’ve worked around products but on t...

When done right, evals can be the backbone of product development, enabling teams to build great products that users love. Done wrong, evals can become a massive time sync that never add any real v...

Here’s a talk I gave for the AI Engineer World Fair (4th June 2025). Recording Summary Slides Downloadable as a PDF here.

Team is the single biggest predictor of success – but there’s no ‘playbook’ yet for what teams building LLM products should look like. At Anterior, we’ve gone from first mover in the health insura...

In 2020, as the peak from the first wave of COVID subsided in the UK, I worked my final shift as a medical doctor. Since then, I’ve worked as a data scientist, founded a VC-backed start-up, been an...