Chapter 2 of 5 · Microsoft AI-103
Implement Generative AI and Agentic Solutions
Building generative apps and RAG with Foundry, building and orchestrating agents, and operating generative AI systems.
- 3topics
- 12 minfast track
- 2diagrams and exhibits
- 30–35%of the exam
Topics in this chapter
Take them in order, or jump to the one you need.
- 1Building Generative Applications with FoundryAI-103 generative apps: connecting to a Foundry project with the SDK, consuming model deployments, retrieval-augmented generation…Diagram4 min
- 2Building Agents with Foundry Agent ServiceAI-103 agents: defining agents, built-in and custom tools, retrieval and memory, multi-agent orchestration, approvals and…Diagram4 min
- 3Optimizing and Operationalizing Generative AIAI-103 tuning and operations: prompt engineering, model parameters, reasoning models, self-critique, tracing and token analytics…4 min
About this chapter
What this chapter covers
Implement Generative AI and Agentic Solutions is the largest AI-103 domain, at 30 to 35% of the exam. It has three skill groups: building generative applications with Foundry, building agents with Foundry, and optimizing and operationalizing generative AI systems.
Expect practical developer questions: which SDK object to create, how to add retrieval, which agent tool fits, how to coordinate several agents, which parameter to change and how to trace a slow request.
How the topics fit together
A generative app calls a model, often grounded with retrieval. An agent adds instructions, tools and conversation state so it can take actions. Several agents can be orchestrated together. Everything is evaluated, traced and tuned before and after release.
Most questions in this domain describe a requirement and ask which feature, tool or setting meets it. Learn what each agent tool and model parameter is for.
How to use these pages
Each topic page has the same shape, so you can skim for what you need.
- What it is: the idea in plain words.
- How it works: the mechanism, with tables and examples.
- What to remember for the exam: the facts to memorise and how questions are phrased.
- Common mistakes: the classic traps.
- Check yourself: three questions to test your understanding.
Ready for more practice?
The full Microsoft AI-103 question bank has 648 questions, with timed practice exams and an explanation for every answer.
This study guide is independent and is not affiliated with, endorsed by, or sponsored by Microsoft. Vendor names, certification names and exam codes are trademarks of their respective owners and are used for identification only.