Markdown source

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

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

slide-001.jpg

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?

slide-002.jpg

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.

slide-003.jpg

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.

slide-004.jpg

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