Skip to content

Microsoft Azure AI Engineer Associate (AI-102)

Exam Overview

The Azure AI Engineer Associate certification validates skills to design and implement AI solutions using Azure AI services, Azure Cognitive Search, and Microsoft Bot Framework. AI Engineers use Azure AI services to build, manage, and deploy AI solutions that leverage pre-built AI models and custom machine learning models.

Exam Details: - Exam Code: AI-102 - Duration: 180 minutes - Number of Questions: 40-60 questions - Passing Score: 700 out of 1000 - Question Types: Multiple choice, multiple select, drag and drop, hot area, case studies, labs - Cost: $165 USD - Prerequisites: Knowledge of Azure and programming languages (C# or Python)

Exam Domains

1. Plan and Manage an Azure AI Solution (15-20%)

  • Select the Appropriate AI Service
  • Select the appropriate service for a computer vision solution
  • Select the appropriate service for a natural language processing solution
  • Select the appropriate service for a speech solution

  • Select the appropriate service for a generative AI solution

  • Plan and Configure Security for an AI Service

  • Plan for AI service security requirements
  • Configure AI service security
  • Manage AI service access keys and endpoints

  • Configure diagnostic logging for an AI service

  • Create and Configure an AI Service

  • Create an AI service
  • Configure AI service endpoints
  • Configure AI service keys and endpoint URLs
  • Manage AI service costs
  • Monitor an AI service

2. Implement Computer Vision Solutions (20-25%)

  • Analyze Images
  • Select visual features to meet image processing requirements
  • Create computer vision solutions to tag images
  • Identify faces and facial features in images
  • Identify custom objects in images
  • Identify image types and image classification
  • Detect domain-specific content in images

  • Detect landmarks and celebrities

  • Implement Custom Computer Vision Models

  • Choose between image classification and object detection models
  • Label images for training
  • Train a custom image model
  • Evaluate custom vision model performance
  • Deploy and test a custom vision model

  • Manage model iterations

  • Analyze Videos

  • Use Video Indexer to analyze videos
  • Extract insights from videos
  • Use the Video Indexer widget and API
  • Customize a Video Indexer model

3. Implement Natural Language Processing Solutions (30-35%)

  • Analyze Text by Using Azure AI Language
  • Extract key phrases from text
  • Extract entities from text
  • Determine sentiment of text
  • Detect the language used in text

  • Detect personally identifiable information (PII) in text

  • Process Speech by Using Azure AI Speech Services

  • Implement text-to-speech solutions
  • Implement speech-to-text solutions
  • Improve text-to-speech by using Speech Synthesis Markup Language (SSML)
  • Implement custom speech solutions

  • Implement intent recognition

  • Translate Language

  • Translate text and documents by using the Azure AI Translator service
  • Implement custom translation solutions
  • Translate speech-to-speech by using the Azure AI Speech service
  • Translate speech-to-text by using the Azure AI Speech service

  • Translate text-to-speech by using the Azure AI Speech service

  • Implement and Manage a Language Understanding Model

  • Create intents and add example utterances
  • Create entities
  • Train, test, publish, and review a Language Understanding model
  • Optimize a Language Understanding model
  • Consume a Language model from a client application

  • Backup and recover Language Understanding models

  • Create a Question Answering Solution

  • Create a knowledge base
  • Import sources to a knowledge base
  • Edit a knowledge base
  • Train and test a knowledge base
  • Publish a knowledge base
  • Create a multi-turn conversation
  • Add alternate phrasing to questions and answers
  • Add chit-chat to a knowledge base
  • Export a knowledge base
  • Create a multi-language question answering solution

4. Implement Knowledge Mining and Document Intelligence Solutions (10-15%)

  • Implement an Azure Cognitive Search Solution
  • Create data sources
  • Define an index
  • Create and run an indexer
  • Query an index, including syntax, sorting, filtering, and wildcards

  • Manage Knowledge Store projections, including file, object, and table projections

  • Implement an Enrichment Pipeline

  • Attach a Cognitive Services account to a skillset
  • Select and include built-in skills for documents

  • Implement custom skills and include them in a skillset

  • Implement an Azure AI Document Intelligence Solution

  • Use prebuilt Document Intelligence models
  • Implement a custom Document Intelligence model
  • Train, test, and publish a custom Document Intelligence model
  • Create a composed Document Intelligence model

5. Implement Generative AI Solutions (10-15%)

  • Use Azure OpenAI Service to Generate Content
  • Provision an Azure OpenAI Service resource
  • Select and deploy an Azure OpenAI model
  • Submit prompts to generate natural language
  • Submit prompts to generate code
  • Use the DALL-E model to generate images

  • Use Azure OpenAI APIs and SDKs

  • Optimize Generative AI

  • Configure parameters to control generative behavior
  • Apply prompt engineering techniques
  • Use your own data with an Azure OpenAI model
  • Fine-tune an Azure OpenAI model

Remember: AI-102 focuses on practical implementation of Azure AI services and requires hands-on experience with AI development and deployment scenarios.