AI Engineer World's Fair 2026 — unofficial import demo

I spent ‘24 and ‘25 structuring the entire written history of biopharma - through drugs, trials, deals, etc. This was a ~500B token effort that translated into a production system now used by 19 of the 20 largest pharmas. We achieved PhD-level performance at scale with 99.95% accuracy over critical concepts.

The hard parts were solving questions of domain and organizational “shape”. This involved identifying which critical concepts and which bundle of tasks were worth the organizational investment to automate. And the biggest spillover win wasn't actually about time savings, it was about refocusing scarce expert judgment on error exhaust - out of which falls potential high value roadmap.

I'll walk through real examples and non-obvious, transferable wins. While the case example is in biopharma, the pattern applies to any business that relies on expert domain judgement to deliver differentiated value.