You’ll explore the types, functions, and real-world applications of AI agents. Through hands-on experience with tools like CrewAI, you’ll learn to build and implement AI agents.

You’ll explore the use of Generative AI (GenAI) as a strategic tool and it will guide users on setting up a GenAI playground, crafting effective prompts, and critically evaluating model responses.

Calibrate how much to trust an AI output and when to override it. Score outputs with a confidence rubric, catalog uncertainty signals that mark tool limits, and make documented trust/override decisions across varied scenarios. Calibrated reliance builds the foundational judgment required to keep AI-augmented decisions safe.

Turn one-off AI use into a system that keeps improving. Design iterative feedback loops, run measured improvement cycles against a metric, and build a personal human-AI learning loop playbook tailored to specific roles.

In this project, you assemble a single, role-specific Human-AI Teaming Playbook that pulls together the course's core skills: a task allocation and reliance map, a context-teaching and role-definition approach, a confidence-calibration method, and a continuous learning loop. You'll be able to justify, in one coherent document, when to lead, follow, or co-work with AI using ChatGPT or Claude. It matters because this playbook is a portfolio-ready artifact you can show a hiring manager, interviewer, or teammate.