---
title: "Dense Slides: WF26: Harness Engineering & Startup Battlefield ft. Garry Tan, Mike Krieger, @t3dotgg , DSPy"
category: "slides"
video_id: "I2cbIws9j10"
sourceLabels: ["Captured video frames", "Local OpenCV slide-region detection", "Local RapidOCR"]
---

# Dense Slides: WF26: Harness Engineering & Startup Battlefield ft. Garry Tan, Mike Krieger, @t3dotgg , DSPy

## Source Video
[WF26: Harness Engineering & Startup Battlefield ft. Garry Tan, Mike Krieger, @t3dotgg , DSPy](https://www.youtube.com/watch?v=I2cbIws9j10)

## Method
This deck is slide-only. The existing captured video frame set supplies candidate frames, then local OpenCV/RapidOCR rejects sponsor/title/speaker-only frames, crops visible slide surfaces, deduplicates, and OCRs the cropped slide images.

## Cropped Visible Slides
![[assets/dense-slides/I2cbIws9j10/slide-001.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/dense/I2cbIws9j10/slide-001.html)
- AI slide classifier: `content_slide` confidence `0.98`
- Text source: none.
- OCR decision: ready — Chart labels and callout text are dense.
![[assets/dense-slides/I2cbIws9j10/slide-002.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/dense/I2cbIws9j10/slide-002.html)
- AI slide classifier: `content_slide` confidence `0.97`
- Text source: none.
- OCR decision: ready — Architecture diagram and small labels are OCR-suitable.
![[assets/dense-slides/I2cbIws9j10/slide-003.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/dense/I2cbIws9j10/slide-003.html)
- AI slide classifier: `content_slide` confidence `0.97`
- Text source: agent_vision.
- OCR decision: ready — Stacked diagram labels are OCR-suitable.

Slide text:

> The Intelligence Layer

![[assets/dense-slides/I2cbIws9j10/slide-004.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/dense/I2cbIws9j10/slide-004.html)
- AI slide classifier: `content_slide` confidence `0.98`
- Text source: agent_vision.

Slide text:

> RL Selects the Response, Not the Facts
> State:
> 1. Failure category
> 2. Risk level
> 3. Retry count
> 4. Drift severity
> 5. Data-quality condition
> Action:
> retry • coerce • rollback • quarantine • escalate • log
> 1. Tabular Q-learning
> 2. Small, interpretable state space
> 3. Low-memory inference
> 4. Inspectable Q-values for every decision

![[assets/dense-slides/I2cbIws9j10/slide-006.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/dense/I2cbIws9j10/slide-006.html)
- AI slide classifier: `content_slide` confidence `0.98`
- Text source: agent_vision.

Slide text:

> (problems) One conversation has to do everything
> Meaning:
> the context window becomes
> - the database,
> - the file system,
> - the memory,
> - the reasoning space

![[assets/dense-slides/I2cbIws9j10/slide-007.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/dense/I2cbIws9j10/slide-007.html)
- AI slide classifier: `content_slide` confidence `0.96`
- Text source: agent_vision.
- OCR decision: ready — Browser screenshot with several small labels and footer text.

Slide text:

> Track narrative state, not numbers

![[assets/dense-slides/I2cbIws9j10/slide-008.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/dense/I2cbIws9j10/slide-008.html)
- AI slide classifier: `content_slide` confidence `0.96`
- Text source: agent_vision.
- OCR decision: ready — Screenshot text and small captions are OCR-suitable.

Slide text:

> Narrated on the fly · rendered to paper

![[assets/dense-slides/I2cbIws9j10/slide-009.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/dense/I2cbIws9j10/slide-009.html)
- AI slide classifier: `content_slide` confidence `0.97`
- Text source: agent_vision.
- OCR decision: ready — Dense slide with chart and small body text.

Slide text:

> Your context window has a hidden RAM bill

![[assets/dense-slides/I2cbIws9j10/slide-010.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/dense/I2cbIws9j10/slide-010.html)
- AI slide classifier: `content_slide` confidence `0.98`
- Text source: agent_vision.
- OCR decision: ready — Diagram-heavy slide with small explanatory text.

Slide text:

> What is TurboQuant

![[assets/dense-slides/I2cbIws9j10/slide-011.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/dense/I2cbIws9j10/slide-011.html)
- AI slide classifier: `content_slide` confidence `0.99`
- Text source: agent_vision.

Slide text:

> what people think the agent is
> model
> runtime / sandbox
> tools
> loop
> framework

![[assets/dense-slides/I2cbIws9j10/slide-012.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/dense/I2cbIws9j10/slide-012.html)
- AI slide classifier: `content_slide` confidence `0.98`
- Text source: agent_vision.
- OCR decision: ready — Code slide with multiple lines and small text.

Slide text:

> Simplified Loop


### Hidden Non-Slide Evidence
- [`slide-005.jpg`](/assets/dense-slides/I2cbIws9j10/slide-005.jpg) — `speaker_stage` confidence `0.99`; speaker intro card

Classification audit: `raw/sources/slide-ai-classification/dense/I2cbIws9j10/audit.json`