This course guides you through the complete journey of building, configuring, and evaluating intelligent agents in UiPath Studio Web, with a strong focus on Generative AI (Gen AI) activities and scalable evaluation strategies. Start by exploring the fundamentals in Build your first agent with Studio Web, where you’ll create your first intelligent agents using both no-code tools and Autopilot. Then deepen your knowledge with Agentic prompt engineering, learning how to design effective prompts that guide AI agents to generate useful, accurate, and structured outputs. Next, in Configure context and escalations for agents, you’ll take your agents from functional to enterprise-ready—grounding their responses in business context and designing escalation flows for human-in-the-loop scenarios. Finally, with Configure evaluations for agents, you’ll learn how to test and refine your agents using structured evaluation sets and powerful scoring methods like LLM-as-a-Judge, Exact Match, and JSON Similarity. By the end of this course, you’ll be able to confidently build and deploy Studio Web agents that are reliable, context-aware, and evaluation-driven. 1. Build your first agent with Studio Web Configure agents using Autopilot and from scratch Understand core agent components: tools, prompts, contexts Build a transcript processing agent Learn agent scoring and evaluation basics 2. Agentic prompt engineering Learn zero-shot, few-shot, and chain-of-thought prompting Apply system vs. user prompts for autonomous agents Explore prompt health scoring and optimization 3. Configure context and escalations for agents Implement grounding with storage buckets Build escalation apps using Action Center Design multi-agent flows combining AI and human decisions 4. Configure evaluations for agents Create evaluation sets and reusable evaluators Use Gen AI scoring with LLM-as-a-Judge Track agent health and ensure enterprise readiness