Building Agents with Foundry

Introduction

This lesson continues the heaviest AI-103 domain, Implement generative AI and agentic solutions (30–35%). In the previous lesson you called models and built RAG flows in code that you controlled step by step. An agent goes one level up: a model plus instructions plus tools plus state, hosted by a service that runs the loop "think, call a tool, observe, answer". Exam questions on this topic test whether you can define an agent's role and goal, choose between built-in tools and your own functions, track conversations, add memory, and wire in APIs, knowledge stores and search.