Dense Slides: Why (Senior) Engineers Struggle to Build AI Agents — Philipp Schmid, Google DeepMind
Source Video
Why (Senior) Engineers Struggle to Build AI Agents — Philipp Schmid, Google DeepMind
Method
This deck is slide-only. The existing captured video frame set supplies candidate frames, then local OpenCV rejects sponsor/title/speaker-only frames, crops visible slide surfaces, deduplicates, and saves the cropped slide images.
Cropped Visible Slides

- Recreated text/layout view: open HTML recreation
- AI slide classifier:
content_slideconfidence0.98 - Text source: none.
- OCR decision: ready — Diagram slide with multiple small labels and compact text blocks.

- Recreated text/layout view: open HTML recreation
- AI slide classifier:
content_slideconfidence0.99 - Text source: agent_vision.
- OCR decision: ready — Text-heavy slide with bullets and embedded code screenshots.
Slide text:
Text is the New State
- The Trap: Treating the real world as enums and booleans because it feels safe.
- The Collision: Forcing natural language intent into discrete booleans lobotomizes the context.
- The Fix: Preserve semantic meaning through raw strings so the agent can adapt intelligently downstream.
Classification audit: raw/sources/slide-ai-classification/dense/3_gYbhABcAE/audit.json