Why We Rebuilt Microsoft Office From Scratch for AI Agents - Yijia Liang, Compound AI

Yijia Liang spent years as a finance analyst living in Excel and PowerPoint before founding Compound to build autonomous AI analysts for institutional investors. Personal agents took off because they run reliably in the background, act on their own and connect to your context, but finance needs more: multiplayer agents with their own inboxes that join deal-team email threads, a headless Office engine rebuilt from scratch with agents (1.5 trillion tokens and over 8 million lines of code) that runs work in parallel and checks its own formatting, and agent swarms that can work through data rooms of 15,000+ files. Chapters: 0:00 Intro 0:52 Why personal agents took off 1:34 Why that breaks in finance 3:12 Multiplayer agents 4:10 An inbox for every agent 5:28 Why off-the-shelf Office tools fall short 6:04 Rebuilding Office from scratch 7:38 Why headless is faster 8:21 Comments and collaboration 9:08 Write, render, check, fix 9:55 Huge data rooms and models 13:10 From copilot to autopilot 15:09 Wrap-up Yijia Liang https://getcompound.ai Join us in SF for the second annual AIE CODE summit: https://aie.codes our last flagship summit of 2026. Applications live now!