Get in Touch
 Duration 14 hours

Course Outline

Revisiting Core AutoGen Concepts

  • Definitions of agents and groups.
  • Function calling and role chaining mechanics.
  • Identifying limitations of built-in agents and the need for customization.

Creating Custom Agents in Python

  • Defining agent behavior through user_proxy and AssistantAgent subclasses.
  • Embedding role-specific logic and decision-making processes.
  • Developing reusable agent modules and mixins.

Advanced Tool Integration and Routing

  • Processes for tool registration, binding, and invocation.
  • Conditionally directing inputs to specific tools.
  • Overseeing multi-step toolchains and composite actions.

Planning and Context Management

  • Designing task decomposers and intermediate planners.
  • Preserving context across chained agents.
  • Implementing scoped memory for extended sessions.

Error Handling and Recovery Strategies

  • Identifying and managing failed or incomplete interactions.
  • Triggering agent retries and fallback logic.
  • Logging, debugging, and validating responses.

Multi-Agent Collaboration with Custom Roles

  • Coordinating specialists within dynamic agent groups.
  • Orchestrating reasoning loops and cooperative workflows.
  • Balancing role separation versus role blending in task allocation.

Real-World Deployment Tactics

  • Optimizing for performance and cost efficiency (e.g., token usage, caching).
  • Integrating AutoGen workflows into web applications or pipelines.
  • Addressing security, observability, and user feedback integration.

Summary and Future Directions

Requirements

  • Strong proficiency in Python programming.
  • Practical experience in building LLM-based applications.
  • Knowledge of function calling and multi-agent system design.

Audience

  • Senior developers.
  • Platform engineers.
  • AI architects.

Testimonials (1)

Related Categories