Prerequisites
Before enrolling in the process of taking the AI-102 exams, candidates should be skilled in implementing Python and C#, using APIs and SDKs based on REST to create natural language processing solutions, computer vision solutions, and knowledge mining and communicative AI solutions based on Azure. In addition, such specialists should be knowledgeable of the elements that create the Azure AI portfolio as well as the data storage options. To add more, they should be able to implement AI principles appropriately.
Microsoft AI-102 Exam Overview:
| Certification Vendor: | Microsoft |
|---|---|
| Exam Name: | Designing and Implementing a Microsoft Azure AI Solution |
| Exam Number: | AI-102 |
| Related Certifications: | Microsoft Certified: Azure AI Engineer Associate |
| Passing Score: | 700 (on a scale of 1-1000) |
| Exam Price: | $165 USD |
| Exam Format: | Case studies, Multiple-choice, Active screen questions, Drag-and-drop |
| Available Languages: | Chinese (Simplified), English, Korean, Japanese |
| Exam Duration: | 120 minutes |
| Certificate Validity Period: | No expiration; certification remains valid unless Microsoft deprecates it |
| Real Exam Qty: | 40-60 |
| Sample Questions: | Microsoft AI-102 Sample Questions |
| Exam Way: | In-person at Pearson VUE testing centers or online proctored exam |
| Pre Condition: | Recommended: Understanding of Azure services, REST APIs, C#, Python, or JavaScript. No mandatory prerequisites, but Azure Administrator or Developer background is beneficial. |
| Official Syllabus URL: | https://learn.microsoft.com/en-us/credentials/certifications/exams/ai-102/ |
Schedule exam
Languages: English, Japanese, Chinese (Simplified), Korean
Retirement date: none
This exam measures your ability to accomplish the following technical tasks: plan and manage an Azure Cognitive Services solutions; implement Computer Vision solutions; implement natural language processing solutions; implement knowledge mining solutions; and implement conversational AI solutions.
Reference: https://docs.microsoft.com/en-us/learn/certifications/exams/ai-102
Exam Details
Speaking of the exam details, the test will contain from 40 to 60 questions of various types which you need to complete within 100 or 120 minutes (depends on the inclusion of labs). To pass the exam you need to schedule the test on the PearsonVUE platform, pay an exam fee which is currently $165, and score at least 700 points or more out of 1000. And, of course, the knowledge of exam topics is a must.
Microsoft AI-102 Exam Syllabus Topics:
| Section | Weight | Objectives |
|---|---|---|
| Topic 1: Implement Computer Vision Solutions | 15-20% | - Implement object detection and image classification - Analyze images using Azure AI Vision - Implement Azure AI Face service - Read and process documents using Azure AI Document Intelligence - Process video and generate insights |
| Topic 2: Implement Generative AI Solutions | 10-15% | - Implement prompt engineering techniques - Apply responsible AI practices - Integrate Azure OpenAI models into applications - Use Azure OpenAI Service for generative AI |
| Topic 3: Implement Natural Language Processing Solutions | 20-25% | - Build question answering solutions - Analyze text using Azure AI Language - Implement speech capabilities using Azure AI Speech - Create conversational AI solutions with Azure AI Bot Service - Translate text and speech |
| Topic 4: Implement Knowledge Mining and Document Intelligence Solutions | 15-20% | - Implement Azure AI Search solutions - Design document processing pipelines - Implement semantic and vector search - Create custom skills for Azure AI Search |
| Topic 5: Implement Decision Support Solutions | 10-15% | - Integrate Azure AI services into applications - Monitor and optimize decision support solutions - Design and implement decision automation |
| Topic 6: Plan and Manage an Azure AI Solution | 15-20% | - Implement governance and compliance for AI solutions - Manage AI costs and resource allocation - Select appropriate Azure AI services and technologies - Plan and configure secure AI solutions |
Microsoft Designing and Implementing a Microsoft Azure AI Solution Sample Questions:
You have an Azure subscription that contains an Azure Al Content Safety resource named CS1.
You create a test image that contains a circle.
You submit the test image to CS1 by using the curl command and the following command-line parameters.
What should you expect as the output?
- A. 7
- B. 0.0
- C. 100
- D. 0
Correct Answer: B 🗳️
Explanation: Only visible for TopExamCollection members. You can sign-up / login (it's free).
You have the following C# function.
You call the function by using the following code.
Following 'key phrases' what output will you receive?
- A. Jumps over the
- B. Quick brown fox lazy dog
- C. The quick brown fox jumps over the lazy dog
- D. The quick
Correct Answer: B 🗳️
Explanation: Only visible for TopExamCollection members. You can sign-up / login (it's free).
Your company wants to reduce how long it takes for employees to log receipts in expense reports. All the receipts are in English.
You need to extract top-level information from the receipts, such as the vendor and the transaction total. The solution must minimize development effort.
Which Azure Cognitive Services service should you use?
- A. Custom Vision
- B. Personalizer
- C. Form Recognizer
- D. Computer Vision
Correct Answer: B 🗳️
Explanation: Only visible for TopExamCollection members. You can sign-up / login (it's free).
You have an existing Azure Cognitive Search service.
You have an Azure Blob storage account that contains millions of scanned documents stored as images and PDFs.
You need to make the scanned documents available to search as quickly as possible. What should you do?
- A. Split the data into multiple blob containers. Create a Cognitive Search service for each container.
Within each indexer definition, schedule the same runtime execution pattern. - B. Split the data into multiple blob containers. Create an indexer for each container. Increase the search units. Within each indexer definition, schedule a sequential execution pattern.
- C. Create a Cognitive Search service for each type of document.
- D. Split the data into multiple virtual folders. Create an indexer for each folder. Increase the search units. Within each indexer definition, schedule the same runtime execution pattern.
Correct Answer: D 🗳️
Explanation: Only visible for TopExamCollection members. You can sign-up / login (it's free).
You are developing a method for an application that uses the Azure Translator in Foundry Tools API.
The method will receive the content of a webpage, and then translate the content into Greek (el). The result will also contain a transliteration that uses the Roman alphabet.
You need to create the URI for the call to the Azure Translator in Foundry Tools API.
You have the following URI.
https://api.cognitive.microsofttranslator.com/translate?api-version=3.0 Which three additional query parameters should you include in the URI? Each correct answer presents part of the solution.
NOTE: Each correct selection is worth one point.
- A. toScript=Cyrl
- B. textType=html
- C. to=el
- D. from=el
- E. toScript=Latn
- F. textType=plain
Correct Answer: B,C,E 🗳️
Viewing page 1 out of 85 pages.
Viewing questions 1-5 out of 425 questions.

We're so confident of our products that we provide no hassle product exchange.


By Troy


