---
title: "Dense Slides: Building AI Agents that actually automate Knowledge Work - Jerry Liu, LlamaIndex"
category: "slides"
video_id: "jVGCulhBRZI"
sourceLabels: ["Captured video frames", "Local OpenCV slide-region detection"]
---

# Dense Slides: Building AI Agents that actually automate Knowledge Work - Jerry Liu, LlamaIndex

## Source Video
[Building AI Agents that actually automate Knowledge Work - Jerry Liu, LlamaIndex](https://www.youtube.com/watch?v=jVGCulhBRZI)

## 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/jVGCulhBRZI/slide-001.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/dense/jVGCulhBRZI/slide-001.html)
- AI slide classifier: `content_slide` confidence `0.99`
- Text source: agent_vision.

Slide text:

> AI Agents can Automate Knowledge Work
> A big promise of AI agents is making knowledge workers more efficient:
> Lower cost, save time
> More data, better decision-making
> Every b2b SaaS is talking about it.
> But does "knowledge work automation" just mean RAG chatbots?

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

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

Slide text:

> The Alpha is in Unstructured Data
> 90% of Enterprise Data Lives in Documents*
> Humans historically needed to read/write these documents.
> For the first time, AI agents can reason and act over massive amounts of unstructured context tokens.

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

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/dense/jVGCulhBRZI/slide-003.html)
- AI slide classifier: `content_slide` confidence `0.99`
- Text source: agent_vision.

Slide text:

> Special Release: Excel!
> We built an Excel agent capable of:
> 1. Data Transformation: Transforming each sheet into a normalized 2D format.
> 2. Agentic QA: Answer questions over cells in any of the sheets.
> This is available in early preview.

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

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

Slide text:

> Automation UX
> Use Cases
> Financial Data Normalization
> Datasheet Extraction
> Patient Record Extraction
> Invoice Reconciliation
> https://github.com/run-llama/invoice-reconciler


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