Generative AI and Agents / 6 weeks
AI Agents and Automation
Teaches builders how to design agents that plan, use tools, and complete tasks reliably, with controls, evaluation, and human oversight that match the risk.
Learning path
Six modules with practical application.
- Goal, policy, planning style, memory, and termination logic that define how an agent decides what to do next
- Defining the right tools for the task, the contract for each, and the rules the agent must follow to call them
- Plan then act, reflect and revise, scratchpads, short and long term memory, and avoiding endless loops
- Building task suites, scoring success, robustness, and safety, and not believing demos
- Designing review checkpoints, approval gates, and rollback paths sized to what the agent can do and what it can damage
- Monitoring, cost, latency, and incident response for systems that take actions in the world
Loading course material…