---
title: "Slides: Browser Agents Don't Need Better Models. They Need Better Eyes. - Kushan Raj, ARK"
category: "slides"
video_id: "JnubYCYunk8"
sourceLabels: ["Public YouTube video frames", "Public YouTube metadata"]
---

# Slides: Browser Agents Don't Need Better Models. They Need Better Eyes. - Kushan Raj, ARK

## Source Video
[Browser Agents Don't Need Better Models. They Need Better Eyes. - Kushan Raj, ARK](https://www.youtube.com/watch?v=JnubYCYunk8)

## Relationship To World's Fair 2026
These slides are extracted from a public AI Engineer YouTube video connected to World's Fair 2026. Speaker-matched clips are supporting context unless later confirmed as exact session recordings; official livestream recordings are day-level/event-level source material.

## Related Scheduled Sessions
- No individual scheduled session mapping has been assigned yet; treat this as an event livestream deck.

## Extracted Slides
![[assets/slides/JnubYCYunk8/slide-007.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/JnubYCYunk8/slide-007.html)
- AI slide classifier: `content_slide` confidence `0.97`
- Text source: agent_vision.

Slide text:

> This browser challenge is a
> Fairly simple webpage
> But generally across webpage
> The markdown has
> ~20x token compression w.r.t DOM

![[assets/slides/JnubYCYunk8/slide-008.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/JnubYCYunk8/slide-008.html)
- AI slide classifier: `content_slide` confidence `0.98`
- Text source: none.
- OCR decision: ready — Dense markdown/code screenshot with small text and multiple sections.

### Hidden Non-Slide Evidence
- [`slide-001.jpg`](/assets/slides/JnubYCYunk8/slide-001.jpg) — `demo_video` confidence `0.99`; Browser demo footage with popups and an app sidebar, not a presentation slide.
- [`slide-002.jpg`](/assets/slides/JnubYCYunk8/slide-002.jpg) — `demo_video` confidence `0.99`; Desktop/file-explorer and terminal screen capture, not a readable presentation slide.
- [`slide-003.jpg`](/assets/slides/JnubYCYunk8/slide-003.jpg) — `demo_video` confidence `0.98`; Screen-recorded browser/terminal demo footage, not a presentation slide.
- [`slide-004.jpg`](/assets/slides/JnubYCYunk8/slide-004.jpg) — `demo_video` confidence `0.99`; Screen-recorded browser/UI footage with an overlaid demo message, not a presentation slide.
- [`slide-005.jpg`](/assets/slides/JnubYCYunk8/slide-005.jpg) — `demo_video` confidence `0.98`; Screen-recording/demo footage with browser UI, webcam bubble, and video controls; not a presentation slide.
- [`slide-006.jpg`](/assets/slides/JnubYCYunk8/slide-006.jpg) — `demo_video` confidence `0.97`; Screen-share/demo footage showing Google AI Studio in a browser with tabs and side panes; not a presentation slide.

Classification audit: `raw/sources/slide-ai-classification/slides/JnubYCYunk8/audit.json`

## Slide-Derived Subjects To Review
Subject extraction uses video title, related session titles/descriptions, transcript context, and OCR text when available. OCR is best-effort and should be reviewed against the embedded slide images.