---
title: "Reconstructed Slides: The emerging skillset of wielding coding agents — Beyang Liu, Sourcegraph / Amp"
category: "slides"
video_id: "F_RyElT_gJk"
sourceLabels: ["Cropped public YouTube video frames", "Local OpenCV slide-region detection", "Local RapidOCR"]
---

# Reconstructed Slides: The emerging skillset of wielding coding agents — Beyang Liu, Sourcegraph / Amp

## Source Video
[The emerging skillset of wielding coding agents — Beyang Liu, Sourcegraph / Amp](https://www.youtube.com/watch?v=F_RyElT_gJk)

## Method
This deck is reconstructed from the existing video frame captures by detecting likely slide regions with OpenCV, cropping/upscaling those regions, deduplicating similar crops, and OCRing the cropped slide images locally. It is a cleaner companion to the full-stage frame deck.

## Reconstructed Slides
![[assets/reconstructed-slides/F_RyElT_gJk/slide-002.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/reconstructed/F_RyElT_gJk/slide-002.html)
- AI slide classifier: `content_slide` confidence `0.95`
- Text source: agent_vision.
- OCR decision: ready — Multi-column slide with embedded social screenshots and small text.

Slide text:

> Are coding agents good or slop?

![[assets/reconstructed-slides/F_RyElT_gJk/slide-003.jpg]]

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

Slide text:

> You are using Cursor AI incorrectly...
> - Using Cursor as a replacement for Google Search.
> - Underspecification of prompts, not knowing how to drive outcomes and using low-level thinking of "implement XYZ, please".
> - Treating Cursor as if it is an IDE, instead of it being an autonomous agent.
> - Blissful unawareness of the concept that you can program LLM outcomes.
> - Unnecessary usage of pleasantries ("please" and "can you") with it as if it were a human. If it fucks up, swear at it - go all caps and call it a clown. It soothes the soul.

![[assets/reconstructed-slides/F_RyElT_gJk/slide-004.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/reconstructed/F_RyElT_gJk/slide-004.html)
- AI slide classifier: `content_slide` confidence `0.99`
- Text source: agent_vision.

Slide text:

> Top mistake:
> Using coding agents like you were using AI coding tools 6 months ago

![[assets/reconstructed-slides/F_RyElT_gJk/slide-005.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/reconstructed/F_RyElT_gJk/slide-005.html)
- AI slide classifier: `content_slide` confidence `0.99`
- Text source: agent_vision.

Slide text:

> GPT-3 → GPT-4, → Claude 4
> Claude 3,
> Gemini 2.5

![[assets/reconstructed-slides/F_RyElT_gJk/slide-006.jpg]]

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

Slide text:

> GPT-3 → GPT-4, → Claude 4
> Claude 3,
> Gemini 2.5
> Copilots → RAG bots → Agents
> What would a coding agent designed to unleash tool LLMs look like?

![[assets/reconstructed-slides/F_RyElT_gJk/slide-007.jpg]]

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

Slide text:

> Controversial design decisions
> - Just make edits - don't ask me
> - Minimal UI - no VS Code fork
> - No "choose your own model"
> - No fixed pricing, no token limit
> - Unix philosophy over vertical integration
> - Don't build on top of a RAG bot - existing code AI UX is now outdated

![[assets/reconstructed-slides/F_RyElT_gJk/slide-008.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/reconstructed/F_RyElT_gJk/slide-008.html)
- AI slide classifier: `content_slide` confidence `0.96`
- Text source: agent_vision.

Slide text:

> RAG context UIs
> Agent UI

![[assets/reconstructed-slides/F_RyElT_gJk/slide-009.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/reconstructed/F_RyElT_gJk/slide-009.html)
- AI slide classifier: `content_slide` confidence `0.98`
- Text source: agent_vision.

Slide text:

> 2 simple clients

![[assets/reconstructed-slides/F_RyElT_gJk/slide-010.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/reconstructed/F_RyElT_gJk/slide-010.html)
- AI slide classifier: `content_slide` confidence `0.97`
- Text source: agent_vision.
- OCR decision: ready — Dense docs/code and embedded UI screenshot; OCR is likely useful.

Slide text:

> Amp

![[assets/reconstructed-slides/F_RyElT_gJk/slide-011.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/reconstructed/F_RyElT_gJk/slide-011.html)
- AI slide classifier: `content_slide` confidence `0.96`
- Text source: agent_vision.

Slide text:

> Amp

![[assets/reconstructed-slides/F_RyElT_gJk/slide-012.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/reconstructed/F_RyElT_gJk/slide-012.html)
- AI slide classifier: `content_slide` confidence `0.96`
- Text source: agent_vision.

Slide text:

> Amp

![[assets/reconstructed-slides/F_RyElT_gJk/slide-013.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/reconstructed/F_RyElT_gJk/slide-013.html)
- AI slide classifier: `content_slide` confidence `0.95`
- Text source: agent_vision.
- OCR decision: ready — Multi-column code and tool output are small and dense; OCR should do better than manual transcription.

Slide text:

> Amp

![[assets/reconstructed-slides/F_RyElT_gJk/slide-014.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/reconstructed/F_RyElT_gJk/slide-014.html)
- AI slide classifier: `content_slide` confidence `0.95`
- Text source: agent_vision.
- OCR decision: ready — Dense assistant output, TODOs, and issue lists are better handled by OCR.

Slide text:

> Amp

![[assets/reconstructed-slides/F_RyElT_gJk/slide-015.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/reconstructed/F_RyElT_gJk/slide-015.html)
- AI slide classifier: `content_slide` confidence `0.95`
- Text source: agent_vision.
- OCR decision: ready — Dense issue list and code-like UI; OCR is appropriate.

Slide text:

> Amp

![[assets/reconstructed-slides/F_RyElT_gJk/slide-016.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/reconstructed/F_RyElT_gJk/slide-016.html)
- AI slide classifier: `content_slide` confidence `0.95`
- Text source: agent_vision.
- OCR decision: ready — Code-heavy split view with small labels and UI text; OCR is appropriate.

Slide text:

> Amp

![[assets/reconstructed-slides/F_RyElT_gJk/slide-017.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/reconstructed/F_RyElT_gJk/slide-017.html)
- AI slide classifier: `content_slide` confidence `0.96`
- Text source: none.
- OCR decision: ready — Dense code/editor screenshot with small labels and diff text.
- Slide text: not surfaced (`none` by AI classifier).
![[assets/reconstructed-slides/F_RyElT_gJk/slide-018.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/reconstructed/F_RyElT_gJk/slide-018.html)
- AI slide classifier: `content_slide` confidence `0.96`
- Text source: none.
- OCR decision: ready — Dense code/editor screenshot with small labels and diff text.
- Slide text: not surfaced (`none` by AI classifier).
![[assets/reconstructed-slides/F_RyElT_gJk/slide-019.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/reconstructed/F_RyElT_gJk/slide-019.html)
- AI slide classifier: `content_slide` confidence `0.95`
- Text source: none.
- OCR decision: ready — Dense code/editor screenshot with explanatory side-panel text and small code diff.
- Slide text: not surfaced (`none` by AI classifier).
![[assets/reconstructed-slides/F_RyElT_gJk/slide-020.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/reconstructed/F_RyElT_gJk/slide-020.html)
- AI slide classifier: `content_slide` confidence `0.98`
- Text source: agent_vision.
- OCR decision: ready — Product UI screenshot with multiple labels and dense interface text.

Slide text:

> External Connectors

![[assets/reconstructed-slides/F_RyElT_gJk/slide-021.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/reconstructed/F_RyElT_gJk/slide-021.html)
- AI slide classifier: `content_slide` confidence `0.98`
- Text source: agent_vision.
- OCR decision: ready — Product modal screenshot with dense form labels and JSON configuration text.

Slide text:

> Edit Connection

![[assets/reconstructed-slides/F_RyElT_gJk/slide-022.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/reconstructed/F_RyElT_gJk/slide-022.html)
- AI slide classifier: `content_slide` confidence `0.95`
- Text source: none.
- OCR decision: ready — Dense code diff plus explanatory bullet text in side panel.
- Slide text: not surfaced (`none` by AI classifier).
![[assets/reconstructed-slides/F_RyElT_gJk/slide-024.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/reconstructed/F_RyElT_gJk/slide-024.html)
- AI slide classifier: `content_slide` confidence `0.91`
- Text source: none.
- OCR decision: ready — Dense collage of social posts and testimonial screenshots; OCR is better than manual transcription.
- Slide text: not surfaced (`none` by AI classifier).

### Hidden Non-Slide Evidence
- [`slide-001.jpg`](/assets/reconstructed-slides/F_RyElT_gJk/slide-001.jpg) — `sponsor_logo` confidence `0.99`; Sponsor/logo wall, not a content slide.
- [`slide-023.jpg`](/assets/reconstructed-slides/F_RyElT_gJk/slide-023.jpg) — `demo_video` confidence `0.99`; Non-slide demo interstitial with only a demo label on a black screen.

Classification audit: `raw/sources/slide-ai-classification/reconstructed/F_RyElT_gJk/audit.json`