Who is this training for?
This course is designed for developers, AI engineers, and technical professionals who want to build applications that work with images and documents using multimodal, agent-driven approaches. It’s best suited for learners with basic programming experience and a general understanding of cloud or AI concepts.
Training objectives
- Design and deploy AI solutions on Azure to extract insights from visual data
- Analyze images and visual content to derive meaningful insights that support business and application scenarios on Azure
- Implement secure and scalable AI workloads on Azure for visual data processing and analysis
- Evaluate and optimize visual data AI solutions using Azure‑native tools and services
Summary
This one‑day course focuses on building intelligent applications that can see, interpret, and reason over images and documents using various multimodal models and agent‑based tools. Learners explore how visual and document inputs can be combined with language models to enable structured data extraction, analysis, and decision‑making workflows. The course emphasizes practical approaches to information extraction, tool orchestration, and grounding model responses in visual data.
Course outline
Learning Path — Extract insights from visual data on Azure
- Module 1 – Develop a Vision‑Enabled Generative AI Application
- Module 2 – Generate Images with AI
- Module 3 – Generate Videos with Microsoft Foundry
- Module 4 – Analyze Images with Content Understanding
- Module 5 – Create a Multimodal Analysis Solution with Azure Content Understanding
- Module 6 – Create an Azure Content Understanding Client Application
- Module 7 – Extract Data with Azure Document Intelligence
- Module 8 – Create a Knowledge Mining Solution with Azure AI Search
Approach and methodology
Practical and structured approach combining focused theory with guided hands‑on workshops. Participants progressively explore how multimodal models, visual inputs, and document‑based data can be used to build intelligent applications through exercises inspired by real professional scenarios, enabling immediate application of the concepts.
They learn to generate images and videos, analyze visual and document content, and build knowledge‑mining solutions using Azure’s core AI tools.
Led by a Microsoft Certified Trainer (MCT), the training emphasizes interactivity and the development of directly transferable skills for building vision‑enabled AI solutions in a professional context.
Prerequisites
- Familiarity with core Azure concepts, including subscriptions, resource groups, and basic Azure servicesB
- asic understanding of AI and machine learning concepts, especially related to visual or image data
- General awareness of Azure AI services or prior experience with Azure‑based AI solutions
- Experience working with data or applications in a cloud environment is helpful but not required
Recommendations
Optional prerequisites:
- Practical knowledge of Microsoft Foundry
- Familiarity with Azure Content Understanding
- Basic understanding of Azure AI Search
- Experience with multimodal analysis (images, documents, audio, video)
- Understanding of generative image and video models
- Knowledge of REST APIs for generative AI
- Basic familiarity with tool‑orchestration workflows
- Understanding of knowledge‑mining solutions
Microsoft complementary courses:
- AI‑103 — Develop AI apps and agents on Azure
- DP‑100 — Designing and Implementing an Azure Machine Learning Solution
- AI‑200 — Develop AI Solutions with Azure OpenAI
- AZ‑400 — Designing and Implementing Microsoft DevOps Solutions
LEGAL NOTICES
© AFI Expertise inc.
© AFI par Edgenda. All rights reserved.
