AI-102Microsoft Azure AI Engineer Associate is retired
Original questions written from the published objectives and cited to official documentation, never recalled exam content. How we verify, why not dumps.
- Exam code
- AI-102
- Cost
- $165USD
- Questions
- 40 to 60
- Duration
- 100minutes
- Passing score
- 700(scale 1-1000)
- Level
- Mid level
- Study guide
- How to prepare
- Format
- Multiple choice, drag-and-drop, hot area, and case studies
What the exam tests
Exam domains and official weightings
The percentage is the exam weighting; the bar is how many verified questions we hold there, so a short bar is where our bank is thin.
- Plan and manage an Azure AI solution23%0 verified
- Implement generative AI solutions18%0 verified
- Implement an agentic solution8%0 verified
- Implement computer vision solutions13%0 verified
- Implement natural language processing solutions19%0 verified
- Implement knowledge mining and information extraction solutions19%0 verified
What the exam actually asks you to do
Multiple choice and multiple response, plus drag-and-drop ordering, hot area items where you click a region of a screenshot, and case studies that hold one scenario across several linked questions.
Item formats
- Multiple choice
- Multiple response
- Drag and drop
- Hot area
- Case study
The highlighted formats are the ones you cannot answer from memory alone. Microsoft Learn, exam duration and question types ↗
Microsoft Azure’s free resources
Study from the source. The page below is free to read, and it is what our own questions are written from.
Official Azure AI Engineer exam page & objectives ↗Keep reading
- Azure AI Engineer exam format
How many questions, how long, what the items look like, and how long it stays valid.
- Azure AI Engineer passing score
The exact cut score, what kind of number it is, and the retake terms.
- How hard is Azure AI Engineer?
An honest difficulty read from the format, the clock and the weights.
Frequently asked questions
What changed recently in AI-102?
The outline now includes implementing agentic solutions alongside generative AI, and Azure AI Foundry carries much of the exam. Prep material written for the older cognitive-services outline misses examinable ground.
How much coding does AI-102 expect?
You read SDK calls and REST payloads in C# or Python and choose the right one. The exam tests wiring services together: keys and endpoints, deployments, prompts and skillsets, rather than model mathematics.
Note on domain weightings
Microsoft publishes weightings as ranges. The figures here use midpoints of the official ranges from the current AI-102 study guide.