Skip to content

Study plan — AI-103 ​

A suggested two-week ramp. Domains 1–2 carry the most weight (55–65% combined), so spend the most time on Foundry models/agents, RAG, and orchestration.

Week 1 — Build the foundation ​

DayFocusPractice
1Read Domain 1: choosing Foundry models & services, deployments—
2Quotas/scaling/cost, monitoring, security, responsible AIDomain 1 quiz
3Read Domain 2: generative apps, RAG, SDKs—
4Agents: tools, function-calling, memory, multi-agent orchestration, observabilityDomain 2 quiz
5Read Domain 3: image/video generation, multimodal understandingDomain 3 quiz
6Read Domain 4: text analysis, speechDomain 4 quiz
7Read Domain 5: retrieval/grounding, document extraction · drill flashcardsFlashcards

Week 2 — Reinforce and simulate ​

DayFocusPractice
8Re-take any quiz scored below 80%Quizzes
9Hands-on: build a Foundry RAG app over Azure AI SearchLabs
10Hands-on: build a Foundry agent with tools + function-callingLabs
11Multiple-response set and case studiesPractice
12Full mock exam, review every missMock exam
13Targeted re-study of the lowest-scoring domainFlashcards
14Second mock exam attempt · light reviewMock exam

Tips for exam day ​

  • Over-invest in Domains 1–2 — they're the majority of the exam.
  • For "which model/service" questions, match the task: LLM vs small vs multimodal, and the right Foundry Tool for grounding, vision, speech, or extraction.
  • For agents, know tools/function-calling, memory, orchestration, and approval/oversight patterns cold.
  • For "most secure" questions, favor managed identity + RBAC + keyless credentials and private networking.
  • For responsible AI, know content filters, evaluators/safety evaluations, tracing, and provenance/audit.

Unofficial study hub. Content grounded in the official Microsoft Learn study guides.