This module focuses on customizing and extending agent behavior. Learners discover how callbacks, streaming, hooks, plugins, skills, and steering mechanisms can be combined to create more interactive, controllable, and adaptable agent experiences. The module emphasizes how these primitives fit together within an agent harness to influence execution and outcomes.

This module examines what context engineering is and how agents maintain context across interactions. Learners explore conversation history management, state persistence, context window considerations, and session management patterns. These concepts provide the foundation for building agents that can support longer-running interactions and multi-user environments.

This module introduces patterns for coordinating multiple agents to solve complex tasks. Learners build agent systems using delegation, graph-based workflows, and swarm architectures. The module demonstrates how individual agents can be combined into larger systems that distribute work, share context, and collaborate to achieve goals.

This module focuses on preparing agent systems for production use. Learners explore evaluation methodologies, deployment architectures, scalability considerations, and operational best practices. By the end of the module, learners will understand how to measure agent performance and deploy reliable agent applications in cloud environments.