1 of 13

2 of 13

3 of 13

Episode #841

Andrew Ng

4 of 13

Episode #867

Andriy Burkov

5 of 13

6 of 13

What the Heck are “Agents” Anyway?

"Programs where LLM outputs control the workflow."

In practice, involves any or all of:

1. Multiple LLM calls

2. LLMs with ability to use Tools

3. An environment where LLMs interact

4. A Planner to coordinate activities

5. Autonomy

jonkrohn.com/talks

7 of 13

Risks of Agent Systems

Unpredictable path

Unpredictable output

Unpredictable costs

"Guardrails ensure your agents behave safely, consistently, and within your intended boundaries"

Monitor

jonkrohn.com/talks

8 of 13

Agentic AI Frameworks

No framework

OpenAI Agents SDK

LangGraph

MCP

CrewAI

AutoGen

…and many, many more!

9 of 13

Model

Context

Protocol

10 of 13

11 of 13

Engineering Team

Engineering Lead

Backend Engineer

Frontend Engineer

Test Engineer

12 of 13

13 of 13

linkedin.com/in/jonkrohn

youtube.com/c/JonKrohnLearns

Free each month:

  • ~80 GPU hours
  • ~3M tokens

jonkrohn.com/talks