Markdown source

Slides: I Run a Fleet of AI Agents Across Three Machines. Here's What Broke. - Kyle Jaejun Lee, KRAFTON

Source Video

I Run a Fleet of AI Agents Across Three Machines. Here's What Broke. - Kyle Jaejun Lee, KRAFTON

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

• Recreated text/layout view: open HTML recreation
• AI slide classifier: content_slide confidence 0.97
• Text source: agent_vision.

Slide text:

The fleet

MacBook

heavy coding + personal projects

macOS · sleeps

Linux A

long-running coding tasks

headless · always-on

Linux B

short-lived personal side projects

headless · always-on

• Recreated text/layout view: open HTML recreation
• AI slide classifier: content_slide confidence 0.95
• Text source: agent_vision.
• OCR decision: ready — product UI screenshot with many small text elements

Slide text:

The fleet, on screen

• Recreated text/layout view: open HTML recreation
• AI slide classifier: content_slide confidence 0.98
• Text source: agent_vision.

Slide text:

I don't compact — I reset.

compact

X slow

X can't choose what survives

X dropped = gone

reset

fresh agent

re-reads the files

continues

• Recreated text/layout view: open HTML recreation
• AI slide classifier: content_slide confidence 0.95
• Text source: agent_vision.
• OCR decision: ready — dense CLI and diagram content with small text

Slide text:

Failure 1 agents do the work instead of dispatching it

• Recreated text/layout view: open HTML recreation
• AI slide classifier: content_slide confidence 0.96
• Text source: agent_vision.
• OCR decision: ready — dense multi-pane terminal/grid layout with small text

Slide text:

Failure 2 panes too small

• Recreated text/layout view: open HTML recreation
• AI slide classifier: content_slide confidence 0.97
• Text source: agent_vision.
• OCR decision: ready — diagram with small labels and embedded terminal-style content

Slide text:

Failure 4 git credentials collide

• Recreated text/layout view: open HTML recreation
• AI slide classifier: content_slide confidence 0.99
• Text source: agent_vision.

Slide text:

Failure 5 the laptop dies

The MacBook loses power or drops off the network — and every in-progress job dies with it.

• Recreated text/layout view: open HTML recreation
• AI slide classifier: content_slide confidence 0.95
• Text source: agent_vision.
• OCR decision: ready — Discord UI screenshot with many small text elements

Slide text:

I forgot which machine I'd built the feature on.

• Recreated text/layout view: open HTML recreation
• AI slide classifier: content_slide confidence 0.97
• Text source: agent_vision.
• OCR decision: ready — Diagram slide with multiple small labels and boxes that are better suited for OCR than manual transcription.

Slide text:

The convergence

• Recreated text/layout view: open HTML recreation
• AI slide classifier: content_slide confidence 0.98
• Text source: agent_vision.

Slide text:

What I'm building on top

Orchestration manager

Kubernetes

If you're running agents at any scale, let's compare notes.

Classification audit: raw/sources/slide-ai-classification/slides/4kYl2_mqmnQ/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.