---
title: "Slides: Why (Senior) Engineers Struggle to Build AI Agents — Philipp Schmid, Google DeepMind"
category: "slides"
video_id: "3_gYbhABcAE"
sourceLabels: ["Public YouTube video frames", "Public YouTube metadata"]
---

# 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](https://www.youtube.com/watch?v=3_gYbhABcAE)

## 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/3_gYbhABcAE/slide-001.jpg]]

OCR text:

> PLATINUM SPONSORS
> Braintrust WorkOS OpenAI

![[assets/slides/3_gYbhABcAE/slide-002.jpg]]

OCR text:

> 3 Teas ne
> 
> ars, Why (Senior) Engineers ss
> 
> ’ bl rs Struggle to Build Al | wei tsacconss |
> Agents En
> 5 mental model collisions from traditional ,
> engineering, and how to fix them. : Agent Reatty
> 
> = Ze
> = AlEngineer
> [nel aU) colds

![[assets/slides/3_gYbhABcAE/slide-003.jpg]]

OCR text:

> oo
> (i
> r 7 rt
> ek
> il dn erate septs
> | aaa | |
> ai can

![[assets/slides/3_gYbhABcAE/slide-004.jpg]]

OCR text:

> PARTY
> .
> Text is the New State
> The Trap: Treating the rea’ world as enuens,
> and boo'eans because it fee's safe
> ra © The Collision: Forcing natural language
> *” a wtent into discrete boo'vans lebotomizes
> 5 4 bd
> the conteat
> re rs « The Fix: Preserve semantic moaning
> tye through raw strings so the agent can adapt Pd
> wnteligently downstream . 7 sete A see oe os ot, ie, wR 8
> on te
> Ed wo.
> al Engi ing the fut eA
> emma CS g
> i a

![[assets/slides/3_gYbhABcAE/slide-005.jpg]]

OCR text:

> AI Engineer
> EUROPE
> HTTPS://AI.ENGINEER

## 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.