Develop AI apps and agents on Azure (AI-103)

This course was designed for software engineers concerned with building, managing and deploying AI solutions that leverage Microsoft Foundry.

By the end of this course, participants should be able to:

• Develop generative AI applications using Microsoft Foundry on Azure
• Design and implement AI agents capable of task execution and orchestration
• Integrate external tools and knowledge sources into agent-based solutions
• Apply multimodal AI techniques to process diverse data types
• Build natural language processing solutions for conversational and text-based scenarios
• Extract, analyse, and reason over visual and complex content
• Design scalable, production-ready AI systems using Azure services

Module 1: Introduction to AI applications and agents on Azure

• Overview of AI application architectures
• Introduction to generative AI concepts
• Understanding agent-based systems and their role in modern AI
• Overview of Microsoft Foundry capabilities
• Azure services for AI development

Module 2: Developing generative AI applications

• Working with foundation models
• Prompt engineering techniques
• Designing application workflows with generative AI
• Managing inputs, outputs, and context
• Evaluating and refining model responses

Module 3: Building AI agents on Azure

• Agent architecture and design patterns
• Task planning and execution
• Managing agent state and memory
• Event-driven and autonomous agent behaviours
• Debugging and monitoring agent performance

Module 4: Integrating tools and knowledge into agentic solutions

• Tool integration patterns for agents
• Connecting agents to APIs and external services
• Knowledge grounding and retrieval techniques
• Implementing retrieval-augmented generation (RAG)
• Managing data sources and context injection

Module 5: Developing natural language AI solutions

• Natural language processing fundamentals
• Conversational AI design
• Text analysis and classification
• Language generation and summarisation
• Building chat-based interfaces

Module 6: Multimodal AI and complex content understanding

• Working with image and text inputs
• Multimodal model capabilities
• Extracting insights from visual data
• Combining modalities in a single workflow
• Handling complex and unstructured content

Module 7: Building scalable AI solutions with Microsoft Foundry

• Application deployment strategies on Azure
• Scaling AI workloads
• Performance optimisation
• Monitoring and logging
• Security and responsible AI considerations

Module 8: Designing production-ready AI systems

• End-to-end solution design
• Architectural best practices
• Managing lifecycle and updates
• Testing and validation strategies
• Real-world use case scenarios

Participants are familiar with Python and have knowledge on using APIs and SDKs to build agents and generative AI solutions on Azure.

• Exam AI-103: Developing AI Apps and Agents on Azure

• Develop AI cloud solutions on Azure (AI-200)
• Operationalize machine learning and generative AI solutions (AI-300)
• Depending on projects, course codes starting with AI-30xx

• Official course book provided to participants