Course curriculum

    1. Course introduction

    1. Chapter introduction

    2. Deterministic Workflows vs. Agentic Systems

    3. Flexibility, consistency and prompt chaining

    4. Code: transcript analysis

    5. Observability in deterministic chains

    6. Chapter summary

    1. Chapter introduction

    2. Agent autonomy

    3. Components of an Agent

    4. Code: Implementing a Basic Agent Loop in Python

    5. Tracking Agent Components with Weave

    6. Understanding your agent’s traces

    7. OpenAI SDK tracing

    8. Chapter summary

    1. Chapter introduction

    2. Memory types for AI Agents

    3. Online vs offline memory

    4. Code: Implementing Memory for Agents

    5. Observability for Memory Systems in Agents

    6. Observability in Agent Memory Systems

    7. Chapter summary

    1. Chapter introduction

    2. When and Why you should use multiple Agents

    3. Multi-Agent Patterns and Orchestration

    4. Code: Agent Handoffs: Implementing Multi-Agent Systems

    5. OpenAI Agents SDK tracing

    6. Observability in Multi-Agent Systems

    7. Debugging Agent Workflows with Visualization

    8. Chapter summary

    1. Chapter introduction

    2. Why evaluate your agents?

    3. LLM as a judge

    4. Code: simple evals with LLM as a judge

    5. Evaluating Multi-Agent Systems: Dashboards and Metrics

    6. Evaluating Agents with Weave Dashboards

    7. Evaluating Multi-Agent Systems

    8. Comparing Agent Performance

    9. Chapter summary

About this course

  • Free
  • 44 lessons
  • 1.5 hours of video content

Discover your potential, starting today