Course Objective & Scope
Enterprise teams building generative AI on Azure often struggle to coordinate multiple model providers, enforce Entra ID and private networking controls, and measure output quality across scattered services. This programme teaches how to build, evaluate and govern end-to-end AI applications and agents using Microsoft Azure AI Foundry and the unified Foundry SDK.
Foundry Hub and Project governance, selecting frontier and open-weight models from the Model Catalog, enterprise RAG with Azure AI Search, Foundry Agent Service, Azure AI Content Safety shields, automated evaluation and OpenTelemetry tracing are covered hands-on. Participants leave with a reusable Foundry project template and a pre-production readiness checklist.
Who Should Attend?
- Software and AI engineers building LLM and agent applications on Azure
- Cloud and solution architects designing enterprise AI platform security and governance
- Data scientists and MLOps engineers responsible for model evaluation and LLMOps
- Prerequisite: Python or C# programming and basic familiarity with Azure services
Key Takeaways
- Configure secure Azure AI Foundry projects with Entra ID RBAC, Private Link and managed connections
- Benchmark and route across models using the Foundry Model Catalog and unified inference API
- Build grounded assistants using Azure AI Search and the Foundry Agent Service
- Enforce Prompt Shields, groundedness detection and content safety guardrails
- Measure quality, latency and token cost using the Foundry Evaluation SDK and OpenTelemetry tracing
Curriculum
Azure AI Foundry Architecture, Governance and SDK
- Hubs, Projects, Managed Identities, Private Endpoints and connection management
- Working with the unified Azure AI Foundry SDK (Python/C#)
Model Catalog, Deployment Options and Cost Control
- Selecting and benchmarking Azure OpenAI, Mistral, Llama, Cohere and Phi models
- Standard (pay-per-token), Provisioned Throughput (PTU) and Batch deployments
Enterprise RAG with Azure AI Search and Foundry Agent Service
- Hybrid + semantic ranker RAG pipelines with document-level ACL filtering
- Stateful threads, tool calling and OpenAPI/MCP integrations in Foundry Agent Service
Azure AI Content Safety and Guardrails
- Configuring Prompt Shields against direct and indirect prompt injection
- Groundedness detection, PII redaction and custom blocklists
Automated Evaluation, Tracing and LLMOps
- Running batch evaluations for relevance, coherence, groundedness and safety
- OpenTelemetry/Application Insights tracing, quota governance and CI/CD pipelines
Other Courses in This Category
-
Enterprise single- and multi-agent orchestration, MCP tool integration, memory and stateful process workflows using Microsoft Agent Framework (unifying Semantic Kernel and AutoGen).
- Live Course
- 5 modules
-
Accelerating the software development lifecycle with GitHub Copilot Agent Mode, Copilot Coding Agent, custom instructions, IDE MCP servers and automated PR review.
- Live Course
- 5 modules
-
Deploying agents built with any framework (Strands, LangGraph, CrewAI) securely and at scale using Amazon Bedrock AgentCore: Runtime, Memory, Identity, Gateway and Observability.
- Live Course
- 5 modules
-
Building model-driven agents with the open-source AWS Strands Agents SDK: @tool decorators, native MCP integration, multi-provider model support, multi-agent patterns and OpenTelemetry tracing.
- Live Course
- 5 modules
-
Managed enterprise RAG with Amazon Bedrock Knowledge Bases (advanced parsing, chunking, hybrid search, reranking) and safety enforcement with Bedrock Guardrails (PII, grounding, content filters).
- Live Course
- 5 modules
-
Training, deploying and governing classical ML models and open-weight LLMs on AWS using Amazon SageMaker AI: Unified Studio, JumpStart, Training, Pipelines, Model Registry and Endpoints.
- Live Course
- 5 modules
Get in touch
