Bringing agents onto the world wide web
Official Schedule Context
- Date/time: 2026-06-30 · 11:40am-12:00pm
- Track/room: Computer Use · Track 7
- Speaker(s): Paul Klein IV
- Session type/status: session · confirmed
Official Description
The web wasn't built for agents. Heavy HTML, human-first UIs, and a DOM that can hijack the model's
context. Still, agents browse it for millions of hours every month through Browserbase, across teams
like Ramp, Shopify, and Lovable. This talk walks through that browser agent harness layer by layer,
from the security boundary between DOM and model to caching, Agent Identity, and the infrastructure
that provisions browsers at scale, and where browser agents go once it is in place.
Related YouTube Video
The Web Browser Is All You Need - Paul Klein IV, Browserbase (speaker-match related prior/adjacent AI Engineer video; captions: English auto-captions).
Transcript Status
Related video transcript availability: English auto-captions. Treat this as supporting context, not a recording of this exact scheduled session unless later confirmed. Not fetched yet.
People
Notes
- Pending transcript synthesis when an official recording or confirmed matching video is available.
Supporting Slides
- youtube YRGjll7uu5w slides — extracted from the related public AI Engineer video.
Slide Evidence
- Slide-only cropped deck: youtube YRGjll7uu5w dense slides (4 viable slide images).
- Related slide/OCR pages:
- youtube YRGjll7uu5w dense slides
- youtube YRGjll7uu5w reconstructed slides
- youtube YRGjll7uu5w slides
- Slide-derived terms:
microsoft,server,https,browser,francisco,worid,sfair,browserbase,june,will,evals,smol,word,sfar,graphite,windsurf,mongobb,mdaily