
2025-05-08 Stanford CE guest lecture
AI Agents:
The future of work and innovation
What are we talking about?
- What is LlamaIndex
- Agent Patterns in LlamaIndex
- Chaining
- Routing
- Parallelization
- Orchestrator-Workers
- Evaluator-Optimizer
- Hands-on coding
- Building an agent in LlamaIndex
- Implementing patterns in LlamaIndex
- Building a multi-agent system
What is LlamaIndex?
Python: docs.llamaindex.ai
TypeScript: ts.llamaindex.ai
LlamaCloud
cloud.llamaindex.ai
LlamaHub

Why LlamaIndex?
- Build faster
- Skip the boilerplate
- Avoid early pitfalls
- Get best practices for free
- Go from prototype to production
What can you build in LlamaIndex?
- Lots of stuff! Especially...
- AI agents
- RAG
What is an agent?
Semi-autonomous software
that uses tools to accomplish a goal
Agentic programming is a new paradigm
When does an agent make sense?
When your data is messy, which is most of the time
LLMs are good at turning lots of text into less text
LLMs work well under the hood
You don't have to build a chatbot
LLMs need data
The solution is RAG
RAG = infinite context

Agents need RAG
and RAG needs agents
Building Effective Agents
- Chaining
- Routing
- Parallelization
- Orchestrator-Workers
- Evaluator-Optimizer
Chaining

Routing

Parallelization

Sectioning

Parallelization: flavor 1
Voting

Parallelization: flavor 2
Orchestrator-Workers

Evaluator-Optimizer
aka Self-reflection

Arbitrary complexity

Workbook time!
What's next?

Thanks!
Follow me on BlueSky:
@seldo.com

AI Agents: the future of work and innovation (Stanford guest lecture)
By Laurie Voss
AI Agents: the future of work and innovation (Stanford guest lecture)
- 86