---
title: "Dense Slides: Mergeable by default: Building the context engine to save time and tokens — Peter Werry, Unblocked"
category: "slides"
video_id: "5ID22ACI7IM"
sourceLabels: ["Captured video frames", "Local OpenCV slide-region detection"]
---

# Dense Slides: Mergeable by default: Building the context engine to save time and tokens — Peter Werry, Unblocked

## Source Video
[Mergeable by default: Building the context engine to save time and tokens — Peter Werry, Unblocked](https://www.youtube.com/watch?v=5ID22ACI7IM)

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

## Cropped Visible Slides
![[assets/dense-slides/5ID22ACI7IM/slide-001.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/dense/5ID22ACI7IM/slide-001.html)
- AI slide classifier: `content_slide` confidence `0.98`
- Text source: agent_vision.

Slide text:

> The problem:
> access ≠ understanding
> - We connect agents to code, logs, docs, tickets, and more...
> - Which gives us plausible output that often compiles...
> - But it fails human review and real world expectations.

![[assets/dense-slides/5ID22ACI7IM/slide-002.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/dense/5ID22ACI7IM/slide-002.html)
- AI slide classifier: `content_slide` confidence `0.94`
- Text source: agent_vision.
- OCR decision: ready — agent marked this slide as OCR-ready

Slide text:

> CODE THAT COMPILES

![[assets/dense-slides/5ID22ACI7IM/slide-003.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/dense/5ID22ACI7IM/slide-003.html)
- AI slide classifier: `content_slide` confidence `0.97`
- Text source: agent_vision.
- OCR decision: ready — agent marked this slide as OCR-ready

Slide text:

> Same prompt. Same model. Different context.

![[assets/dense-slides/5ID22ACI7IM/slide-004.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/dense/5ID22ACI7IM/slide-004.html)
- AI slide classifier: `content_slide` confidence `0.99`
- Text source: agent_vision.

Slide text:

> Workshop setup
> 1 Join the Slack workspace
> 2 Get a GitHub repo invite
> 3 Get an Unblocked invite
> 4 Wire up Unblocked MCP


Classification audit: `raw/sources/slide-ai-classification/dense/5ID22ACI7IM/audit.json`