---
title: "Slides: Recursive Coding Agents - Raymond Weitekamp, OpenProse"
category: "slides"
video_id: "3hXJI2q0Jz8"
sourceLabels: ["Public YouTube video frames", "Public YouTube metadata"]
---

# Slides: Recursive Coding Agents - Raymond Weitekamp, OpenProse

## Source Video
[Recursive Coding Agents - Raymond Weitekamp, OpenProse](https://www.youtube.com/watch?v=3hXJI2q0Jz8)

## 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/3hXJI2q0Jz8/slide-001.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/3hXJI2q0Jz8/slide-001.html)
- AI slide classifier: `title_card` confidence `0.97`
- Text source: agent_vision.

Slide text:

> Recursive Coding Agents
> Raymond Weitekamp
> RAW.works | OpenProse
> @raw_works

![[assets/slides/3hXJI2q0Jz8/slide-002.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/3hXJI2q0Jz8/slide-002.html)
- AI slide classifier: `content_slide` confidence `0.99`
- Text source: agent_vision.

Slide text:

> We all want outcomes.
> Agents that work on our behalf - reliable co-workers - while we're out on a hike.
> The bottleneck is not intelligence. It's reliability. It's trust.
> One day - my agents build me a full SaaS app from a single prompt.
> The next day - they empty the entire contents of my Solana wallet.

![[assets/slides/3hXJI2q0Jz8/slide-003.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/3hXJI2q0Jz8/slide-003.html)
- AI slide classifier: `content_slide` confidence `0.98`
- Text source: agent_vision.
- OCR decision: ready — Dense slide with screenshot cards and small captions; OCR is better suited than manual transcription for the embedded text.

Slide text:

> Today's agents are mismanaged geniuses

![[assets/slides/3hXJI2q0Jz8/slide-004.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/3hXJI2q0Jz8/slide-004.html)
- AI slide classifier: `content_slide` confidence `0.98`
- Text source: agent_vision.
- OCR decision: ready — Contains a paper screenshot plus small diagram labels and bullet text; OCR should recover the embedded text more reliably.

Slide text:

> Context itself is the object of computation

![[assets/slides/3hXJI2q0Jz8/slide-005.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/3hXJI2q0Jz8/slide-005.html)
- AI slide classifier: `content_slide` confidence `0.98`
- Text source: agent_vision.
- OCR decision: ready — Dense comparison table with multiple columns and rows; OCR is the right extraction method.

Slide text:

> Lots of things feel close.

![[assets/slides/3hXJI2q0Jz8/slide-006.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/3hXJI2q0Jz8/slide-006.html)
- AI slide classifier: `content_slide` confidence `0.99`
- Text source: agent_vision.
- OCR decision: ready — Two-column slide with code-like examples and fine text; OCR is better than manual transcription here.

Slide text:

> OpenProse explicitly declares subagent work

![[assets/slides/3hXJI2q0Jz8/slide-007.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/3hXJI2q0Jz8/slide-007.html)
- AI slide classifier: `content_slide` confidence `0.99`
- Text source: agent_vision.

Slide text:

> Recursive Coding Agents FTW
> Trust is reliability
> A new paradigm of inference-time compute
> Coding agents can be RLMs


Classification audit: `raw/sources/slide-ai-classification/slides/3hXJI2q0Jz8/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.