Evaluating and Operating Agentic AI Systems

Everything you need for the labs and assessment. PDF files print cleanly; Markdown files open in any editor.

• Course slides (PowerPoint)PPTX 1.1 MB PPTX
• Course syllabusPDF 100 KB · MD 4 KB PDF MD
• Lab guidePDF 304 KB · MD 26 KB PDF MD
• Worksheet W1: Failure taxonomy and evaluation planPDF 56 KB · MD 1 KB PDF MD
• Worksheet W2: Golden dataset, graders, and judge-agreement reportPDF 41 KB · MD 1 KB PDF MD
• Worksheet W3: Component and trajectory scorecardPDF 52 KB · MD 1 KB PDF MD
• Worksheet W4: Reliability, cost, and red-team reportPDF 42 KB · MD 1 KB PDF MD
• Worksheet W5: Agent Evaluation and Operations Plan (capstone)PDF 53 KB · MD 2 KB PDF MD
• Quick-reference cardPDF 83 KB · MD 1 KB PDF MD
• Session 1 Handout: Why Agents Fail and How to See ItPDF 117 KB · MD 3 KB PDF MD
• Session 2 Handout: Graders You Can TrustPDF 103 KB · MD 2 KB PDF MD
• Session 3 Handout: Evaluating Agent Behavior End to EndPDF 105 KB · MD 2 KB PDF MD
• Session 4 Handout: Reliability, Cost, and SecurityPDF 103 KB · MD 3 KB PDF MD
• Session 5 Handout: Operating Agents in ProductionPDF 103 KB · MD 2 KB PDF MD
• ProjectsPDF 125 KB · MD 7 KB PDF MD
• Reading listPDF 127 KB · MD 7 KB PDF MD