fr
en
Develop AI applications and agents on Azure (AI-103)
Move from AI prototypes to applications and agents designed for organisational needs. With Azure and Microsoft Foundry, select suitable models, connect data and orchestrate interactions while integrating security and evaluation. Develop deployable AI solutions and prepare for AI-103.
- Duration
- 4 days 28 hours
- Code
- AI-103T00 Code
- Certification
- Microsoft Certified : Azure AI Apps and Agents Developer Associate Certification
Accredited training for the Microsoft Certified : Azure AI Apps and Agents Developer Associate certification.
Presentation
The rise of generative AI and autonomous agents is transforming application design. On Azure, this evolution is embodied in Microsoft Foundry, a unified platform bringing together models, tools and services previously spread across separate cognitive solutions.
This 4-day course teaches you to build robust, secure AI solutions. Cover RAG architecture design, multi-agent orchestration, computer vision and text analysis integration, and automated document information extraction. Each module uses real practical cases with the Foundry SDK.
The programme also prepares you to take AI-103, included in your offer. Passing earns Microsoft Certified: Azure AI Apps and Agents Developer Associate, recognised by Microsoft for technical professionals building Azure AI solutions (see the Certification tab for details).
Objectives
By the end of this course, you will be able to:
- plan and manage an end-to-end Azure AI solution;
- select the appropriate Foundry model and service for each task, including large, small and multimodal language models;
- design and implement generative and agentic AI solutions using RAG, vector and hybrid search, multi-agent orchestration and function calling;
- design and implement computer vision solutions;
- design and implement text analysis and speech processing solutions;
- design and implement document information extraction using OCR and Content Understanding;
- configure AI solution security and guardrails, including managed identity, safety filters and risk detection;
- pass AI-103 and earn Microsoft Certified: Azure AI Apps and Agents Developer Associate certification.
Program
Module 1: Planning and managing an Azure AI solution
- Selecting the appropriate Foundry model and service for each task:
- large and small language models;
- multimodal models and Foundry tools.
- Designing Azure infrastructure for AI applications and agents:
- choosing retrieval and indexing methods;
- integrating memory, tools and knowledge for agentic solutions.
- Securing an Azure AI solution:
- configuring managed identity and private networking;
- configuring safety filters, guardrails and risk detection.
Lab
- Plan and secure an Azure AI solution architecture.
Module 2: Implementing generative and agentic AI solutions
- Designing retrieval-augmented generation solutions:
- grounding, citations and source traceability;
- vector and hybrid search.
- Designing agentic workflows:
- function calling and tool integration;
- memory and approvals in agent workflows;
- multi-agent orchestration;
- agent monitoring and tracing.
- Prompt engineering to optimise responses.
Lab
- Build an agent with RAG, function calling and vector search using the Foundry SDK.
Module 3: Implementing computer vision solutions
- Image analysis: classification, object detection and text extraction.
- Training and publishing a custom vision model.
- Analysing video and live streams.
Lab
- Implement a computer vision solution with a Foundry model.
Module 4: Implementing text analysis and speech solutions
- Text analysis: key phrase extraction, sentiment analysis and personally identifiable information detection.
- Translating text and documents.
- Speech processing:
- speech synthesis and recognition;
- integrating voice as an agent modality.
Lab
- Build a speech-to-text and text-to-speech flow for agentic interaction.
Module 5: Implementing information extraction solutions
- Information extraction through multimodal pipelines using OCR, layout analysis and field extraction.
- Using Content Understanding to produce representations usable by agents and RAG solutions.
- Creating analysers to generate structured outputs for downstream reasoning.
Lab
- Extract and structure document data with Content Understanding for use by an agent.
Audience
This course is intended for professionals designing Azure AI solutions, including:
- software developers designing and deploying AI applications and agents with Microsoft Foundry;
- AI engineers implementing computer vision, text analysis and information extraction solutions;
- solution architects designing secure, scalable AI application architectures on Azure.
Prerequisites
The following prerequisites apply:
- Development skills: practical experience developing applications in Python.
- AI knowledge: familiarity with general AI, generative AI and Azure service capabilities.
- Technical skills: ability to use REST APIs and SDKs.
Good to know: if you are new to Azure or foundational AI concepts, we recommend first taking Microsoft Azure AI Fundamentals (AI-901).
Teaching and assessment methods
- Initial skills assessment
- Training materials provided to participants
- Continuous assessment throughout the course
- End-of-course feedback questionnaire
- Combination of theory and practical application
- Attendance records
- Post-course follow-up evaluation
- Practical exercises
Course highlights
- Up-to-date content: a programme built around Microsoft Foundry, generative AI and agentic architectures, including RAG, multi-agent orchestration and function calling, aligned with the current Microsoft syllabus.
- Expert trainer: a certified Microsoft Azure AI specialist sharing practical experience of production AI application and agent development.
- Practical approach: a lab in every module to build real AI applications and agents using the Foundry SDK, from design to security.
- Certification included: the AI-103 examination is included without additional fees.
Dates and sessions
Choose the date and delivery format that suit you.
No upcoming sessions are currently available.
Microsoft®, Microsoft Azure® and Microsoft Foundry® are registered trademarks or trademarks of Microsoft Corporation in the United States and other countries.