Most of the Web Will Never Get APIs for AI Agents | Dhruv Batra

Most of the web will never get APIs for AI agents. School district sites, small business pages, government offices, and the long tail of e-commerce were built for humans, and they will keep working that way for years. So how do agents actually get things done across the web?Dhruv Batra is co-founder and chief scientist of Yutori, the company building specialized browser and computer-use agents. He previously led embodied AI at Meta's FAIR lab, training robots in simulation and shipping the image question-answering model on Ray-Ban Meta glasses. His bet: the web is a shared roadway, much like roads split between human drivers and self-driving cars, and agents will be built to use it the way people already do.Pixels in, clicks out. That is the API.In this conversation:Why the long tail of the web won't re-architect itself for agentsHow Yutori's Navigator perceives pixels and writes JavaScript on the fly to shorten task trajectoriesWhy Navigator runs 2-3x faster and 4-5x cheaper than Opus 4.7 and GPT-5.5 on browser tasksLearning from live websites, and using URL query parameters as privileged verifiers instead of cloning sitesWhat the shift from American to Chinese open-weight models means for startupsHow smart glasses and robots share the same perception-action loopWhy demand for inference compute is pushing models smaller and onto devicesChapters:(00:00) Pixels in, clicks out (01:37) Why most of the web will never get APIs (08:47) Aggregation, specialization, and human friction (11:39) Digital niches and specialized models (16:41) The web's heavy tail and where browser agents win (20:40) Inside Yutori's Navigator and Scouts (24:08) N1.5: writing JavaScript to cut trajectory length (27:45) Training on live websites (33:29) Open source: FAIR's legacy and the Chinese frontier (37:22) Agent frameworks: OpenClaw, Hermes, heartbeats (40:57) How non-technical users adopt agents (44:25) Smart glasses, robotics, and embodied AI (50:57) Compute demand and smaller on-device models (53:12) Why the company is called YutoriConnect with Dhruv Batra:LinkedIn: https://www.linkedin.com/in/dhruv-batra-dbatra/X/Twitter: https://x.com/DhruvBatra_Yutori: https://yutori.comConnect with Chain of Thought host Conor Bronsdon:Newsletter: https://newsletter.chainofthought.show/Twitter/X: https://x.com/ConorBronsdonLinkedIn: https://www.linkedin.com/in/conorbronsdon/YouTube: https://www.youtube.com/@ConorBronsdonMore episodes: https://chainofthought.show