AI-103 skill area 1 of 5 · exam weight 25–30%

Plan and manage an Azure AI solution

Choosing Foundry services and models, setting up and deploying solutions, operating them securely, and applying responsible AI.

Plan and manage an Azure AI solution carries 25–30% of the AI-103 exam. The study guide splits it into four skill groups: choosing the appropriate Microsoft Foundry services for generative AI and agents, setting up AI solutions in Foundry, managing, monitoring and securing AI systems, and implementing responsible AI across generative AI and agentic systems.

Planning starts with choices. The guide expects you to pick an appropriate model for each task, whether that's a large language model, a small language model, a multimodal model or one of the Foundry Tools, and to choose the Foundry services that fit generative tasks, grounding, vector search, agent workflows or multimodal processing. It also covers choosing a method for retrieval and indexing, and the memory, tool and knowledge integration services an agent solution needs.

Setting up a solution means designing the Azure infrastructure for AI apps and agent-based solutions, choosing deployment options, configuring model and agent deployments, and integrating Foundry projects with CI/CD pipelines. Operating it covers quotas, scaling, rate limits and cost footprints; monitoring model performance, drift, safety events and grounding quality, as well as data ingestion quality, search index health and relevance; and security through managed identity, private networking, keyless credentials and role policies.

Responsible AI closes the area: safety filters, guardrails, risk detection and content moderation; evaluators, safety evaluations and explanation tooling; auditing through trace logging, provenance metadata and approval workflows; and governing agent behavior with oversight modes, constraints and tool-access controls.

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

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

1.1 Choose the appropriate Foundry services for generative AI and agents

The study guide lists these skills:

Choose an appropriate model for each task, including large language models (LLMs), small language models, multimodal models, and Foundry Tools
Choose the appropriate Foundry services for generative tasks, grounding, vector search, agent workflows, or multimodal processing
Choose an appropriate method for retrieval and indexing
Choose appropriate memory, tool, and knowledge integration services for agent solutions

1.2 Set up AI solutions in Foundry

The study guide lists these skills:

Design Azure infrastructure for AI apps and agent-based solutions
Choose appropriate deployment options
Configure model and agent deployments
Integrate Foundry projects with continuous integration and continuous deployment (CI/CD) pipelines

1.3 Manage, monitor, and secure AI systems

The study guide lists these skills:

Manage quotas, scaling, rate limits, and cost footprints for model and agent workloads
Monitor model performance, drift, safety events, and grounding quality
Monitor data ingestion quality, search index health, and relevance performance
Configure security, including managed identity, private networking, keyless credentials, and role policies

1.4 Implement responsible AI across generative AI and agentic systems

The study guide lists these skills:

Configure safety filters, guardrails, risk detection, and content moderation
Apply responsible AI instrumentation, including evaluators, safety evaluations, and explanation tooling
Implement auditing through trace logging, provenance metadata, and approval workflows
Govern agent behavior with oversight modes, constraints, and tool-access controls

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