Markdown source

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

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

• Recreated text/layout view: open HTML recreation
• 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.

• Recreated text/layout view: open HTML recreation
• 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

• Recreated text/layout view: open HTML recreation
• 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.

• Recreated text/layout view: open HTML recreation
• 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