1. Plan and manage an Azure AI solution (20–25%)
Select the appropriate Microsoft Foundry Services
Select the appropriate service for a generative AI solution
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 an information extraction solution
Select the appropriate service for a knowledge mining solution
Plan, create and deploy a Microsoft Foundry Service
Plan for a solution that meets Responsible AI principles
Create an Azure AI resource
Choose the appropriate AI models for your solution
Deploy AI models using the appropriate deployment options
Install and utilize the appropriate SDKs and APIs
Determine a default endpoint for a service
Integrate Microsoft Foundry Services into a CI/CD pipeline
Plan and implement a container deployment
Manage, monitor, and secure a Microsoft Foundry Service
Monitor an Azure AI resource
Manage costs for Microsoft Foundry Services
Manage and protect account keys
Manage authentication for a Microsoft Foundry Service resource
Implement AI solutions responsibly
Implement content moderation solutions
Configure responsible AI insights, including content safety
Implement responsible AI, including content filters and blocklists
Prevent harmful behavior, including prompt shields and harm detection
Design a responsible AI governance framework
2. Implement generative AI solutions (15–20%)
Build generative AI solutions with Microsoft Foundry
Plan and prepare for a generative AI solution
Deploy a hub, project, and necessary resources with Microsoft Foundry
Deploy the appropriate generative AI model for your use case
Implement a prompt flow solution
Implement a RAG pattern by grounding a model in your data
Evaluate models and flows
Integrate your project into an application with Microsoft Foundry SDK
Utilize prompt templates in your generative AI solution
Use Azure OpenAI in Foundry Models
Provision an Azure OpenAI resource
Select and deploy an Azure OpenAI model
Submit prompts to generate code and natural language responses
Use the DALL-E model to generate images
Integrate Azure OpenAI into your own application
Use large multimodal models
Optimize and operationalize generative AI
Configure parameters to control generative behavior
Configure monitoring and diagnostics
Optimize and manage deployment resources
Enable tracing and collect feedback
Implement model reflection
Deploy containers for edge use
Implement orchestration of multiple models
Apply prompt engineering techniques
Fine-tune a generative model
3. Implement an agentic solution (5–10%)
Create custom agents
Understand the role and use cases of an agent
Configure resources to build an agent
Create an agent with Microsoft Foundry Agent Service
Implement complex agents with Microsoft Agent Framework
Implement multi-agent workflows and orchestration
Test, optimize, and deploy an agent
4. Implement computer vision solutions (10–15%)
Analyze images
Select visual features for processing
Detect objects and generate tags
Include image analysis features in requests
Interpret image processing responses
Extract text using Azure Vision
Convert handwritten text
Implement custom vision models
Choose between classification and detection
Label images
Train models
Evaluate model metrics
Publish models
Consume models
Build models code-first
Analyze videos
Use Video Indexer for insights
Use spatial analysis for movement detection
5. Implement natural language processing solutions (15–20%)
Analyze and translate text
Extract key phrases and entities
Determine sentiment
Detect language
Detect PII
Translate text and documents
Process and translate speech
Integrate generative AI speech
Implement text-to-speech and speech-to-text
Use SSML
Implement custom speech solutions
Implement intent and keyword recognition
Translate speech
Implement custom language models
Create intents, entities, and utterances
Train and evaluate models
Optimize and recover models
Consume models in applications
Create question answering projects
Train and publish knowledge bases
Create multi-turn conversations
Add alternate phrasing and chit-chat
Export knowledge bases
Create multilingual solutions
Implement custom translation models
6. Implement knowledge mining and information extraction solutions (15–20%)
Implement Azure AI Search
Provision resource and create index
Create data sources and indexers
Implement custom skills
Create and run indexers
Query indexes
Manage knowledge store projections
Implement semantic and vector search
Implement Document Intelligence
Provision resource
Use prebuilt models
Implement custom models
Train and publish models
Create composed models
Extract information with Content Understanding
Create OCR pipelines
Summarize and classify documents
Extract entities, tables, and images
Process and ingest multimedia data
