---
title: "Slides: You Can't Prompt the Room: The Last Skill AI Won't Replace - Balázs Horváth, VisualLabs"
category: "slides"
video_id: "6bmM45jkMDY"
sourceLabels: ["Public YouTube video frames", "Public YouTube metadata"]
---

# Slides: You Can't Prompt the Room: The Last Skill AI Won't Replace - Balázs Horváth, VisualLabs

## Source Video
[You Can't Prompt the Room: The Last Skill AI Won't Replace - Balázs Horváth, VisualLabs](https://www.youtube.com/watch?v=6bmM45jkMDY)

## 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/6bmM45jkMDY/slide-001.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/6bmM45jkMDY/slide-001.html)
- AI slide classifier: `title_card` confidence `0.98`
- Text source: agent_vision.

Slide text:

> You can't prompt the room.
> Cheap to build. Expensive to decide.

![[assets/slides/6bmM45jkMDY/slide-002.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/6bmM45jkMDY/slide-002.html)
- AI slide classifier: `content_slide` confidence `0.97`
- Text source: agent_vision.

Slide text:

> WHERE THIS STARTS
> 17 of 21 agents abandoned
> On data access. None of them reached the model.

![[assets/slides/6bmM45jkMDY/slide-003.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/6bmM45jkMDY/slide-003.html)
- AI slide classifier: `title_card` confidence `0.97`
- Text source: agent_vision.

Slide text:

> THE BRIDGE
> I've always prompted the developers.
> The room was always the hard part.
> 13 years, ERP & CRM
> US · UK · Hungary
> VisualLabs, Microsoft partner

![[assets/slides/6bmM45jkMDY/slide-004.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/6bmM45jkMDY/slide-004.html)
- AI slide classifier: `content_slide` confidence `0.98`
- Text source: agent_vision.

Slide text:

> THE SHIFT
> The bottleneck moved.
> USED TO BE getting the code built
> NOW deciding what to build

![[assets/slides/6bmM45jkMDY/slide-005.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/6bmM45jkMDY/slide-005.html)
- AI slide classifier: `content_slide` confidence `0.98`
- Text source: agent_vision.

Slide text:

> WHY A MODEL CAN'T DO IT
> Ask it what to build.
> You get a faster horse.
> what already exists
> the average
> a faster horse

![[assets/slides/6bmM45jkMDY/slide-006.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/6bmM45jkMDY/slide-006.html)
- AI slide classifier: `content_slide` confidence `0.98`
- Text source: agent_vision.

Slide text:

> WHY A MODEL CAN'T DO IT
> Ask it what to build.
> You get a faster horse.
> what already exists
> the average
> a faster horse

![[assets/slides/6bmM45jkMDY/slide-007.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/6bmM45jkMDY/slide-007.html)
- AI slide classifier: `content_slide` confidence `0.95`
- Text source: agent_vision.
- OCR decision: ready — Small multi-row diagram text and dense labels are better suited for OCR than manual transcription.

Slide text:

> THE STORY MAP

![[assets/slides/6bmM45jkMDY/slide-008.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/6bmM45jkMDY/slide-008.html)
- AI slide classifier: `content_slide` confidence `0.95`
- Text source: agent_vision.
- OCR decision: ready — Small multi-row diagram text and dense labels are better suited for OCR than manual transcription.

Slide text:

> THE STORY MAP

![[assets/slides/6bmM45jkMDY/slide-009.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/6bmM45jkMDY/slide-009.html)
- AI slide classifier: `content_slide` confidence `0.98`
- Text source: agent_vision.
- OCR decision: ready — Diagram slide with multiple small labels and compact boxes; OCR is likely more reliable than manual transcription.

Slide text:

> THE STORY MAP

![[assets/slides/6bmM45jkMDY/slide-010.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/6bmM45jkMDY/slide-010.html)
- AI slide classifier: `content_slide` confidence `0.99`
- Text source: agent_vision.

Slide text:

> BEFORE THE AGENTS START
> 1 Whose problem is this?
> 2 What does winning look like for them?
> 3 What would make them refuse to use it?
> 4 What decision does it change?

![[assets/slides/6bmM45jkMDY/slide-011.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/6bmM45jkMDY/slide-011.html)
- AI slide classifier: `title_card` confidence `0.99`
- Text source: agent_vision.

Slide text:

> Build the right thing.
> Not the next thing.
> Balazs Horvath
> linkedin.com/in/Balazshorvathd365
> SCAN TO CONNECT


Classification audit: `raw/sources/slide-ai-classification/slides/6bmM45jkMDY/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.