AI-103 skill area 2 of 5 · exam weight 30–35%

Implement generative AI and agentic solutions

Building generative apps and agents with Foundry, then tuning, observing and orchestrating them in production.

Implement generative AI and agentic solutions is the largest skill area on the AI-103 exam, at 30–35%. The study guide groups it into three parts: building generative applications by using Foundry, building agents by using Foundry, and optimizing and operationalizing generative AI systems.

For generative applications, the guide lists deploying and consuming LLMs, small models, code models and multimodal models; implementing retrieval-augmented generation (RAG) in an application; designing workflows, tool-augmented flows and multistep reasoning pipelines; evaluating models and apps for fabrications, relevance, quality and safety; integrating generative workflows by using Foundry SDKs and connectors; and configuring an application to connect to a Foundry project.

For agents, it covers defining agent roles, goals, the conversation-tracking approach and tool schemas; building agents that integrate retrieval, function calling and conversation memory; integrating agent tools such as APIs, knowledge stores, search, content understanding and custom functions; implementing orchestrated multi-agent solutions; building autonomous or semiautonomous workflows with safeguards and approval flow controls; and monitoring deployed agents, evaluating their behavior and performing error analysis.

Optimizing and operationalizing means tuning generation behavior with prompt engineering and model parameters, implementing model reflection, chain-of-thought evaluations and self-critique loops, setting up observability with tracing, token analytics, safety signals and latency breakdowns, and orchestrating multiple models, flows, or hybrid LLM and rules engines.

Source: Microsoft's AI-103 study guide (skills measured as of April 16, 2026). Documentation: Microsoft Foundry documentation.

83 practice questions in this area, covering 16 of 16 study-guide skills.

2.1 Build generative applications by using Foundry

The study guide lists these skills:

Deploy and consume LLMs, small models, code models, and multimodal models
Implement retrieval-augmented generation (RAG) in an application
Design workflows, tool-augmented flows, and multistep reasoning pipelines
Evaluate models and apps, including detecting fabrications, relevance, quality, and safety
Integrate generative workflows into applications by using Foundry SDKs and connectors
Configure an application to connect to a Foundry project

2.2 Build agents by using Foundry

The study guide lists these skills:

Define agent roles, goals, conversation-tracking approach, and tool schemas
Build agents that integrate retrieval, function-calling, and conversation memory
Integrate agent tools, including APIs, knowledge stores, search, content understanding, and custom functions
Implement orchestrated multi-agent solutions
Build autonomous or semiautonomous workflows with safeguards and approval flow controls
Integrate monitoring into deployed agents, evaluate agent behavior, and perform error analysis

2.3 Optimize and operationalize generative AI systems

The study guide lists these skills:

Tune generation behavior, such as prompt engineering and adjusting model parameters
Implement model reflection, chain-of-thought evaluations, and self-critique loops
Set up observability by implementing tracing, token analytics, safety signals, and latency breakdowns
Orchestrate multiple models, flows, or hybrid LLM and rules engines

Practise all 5 skill areas in one quiz, with instant feedback after every answer. Start a quiz →