Coursera Spring Sale
40% Off Coursera Plus Annual!
Grab it
Learn to evaluate AI agent reliability through a hands-on workshop that introduces the Agent GPA (Goal-Plan-Action) framework using the open source TruLens library. Code along with the instructor to measure agent performance across three critical dimensions: goals, plans, and actions, while identifying internal errors such as hallucinations, poor tool usage, and missed planning steps. Gain practical experience implementing evaluation metrics that assess how well AI agents understand objectives, formulate coherent plans, and execute appropriate actions. Access provided code notebooks and slides to follow along with real-world examples and build your own agent evaluation systems using industry-standard tools and methodologies.
