Microsoft's skills measured for AI-103 as of April 16, 2026, mapped to the chapters of Ultra Transcenders AI-103: Developing AI Apps and Agents on Azure.
| Objective | Chapters |
|---|---|
| Plan and manage an Azure AI solution (25–30%) | |
| Choose the appropriate Foundry services for generative AI and agents | 1. Microsoft Foundry: models, resources and deployments; 5. Building generative applications: prompts, parameters and quality; 6. Building agents with Foundry Agent Service; 12. Azure AI Search and retrieval-augmented generation |
| Set up AI solutions in Foundry | 1. Microsoft Foundry: models, resources and deployments; 2. Securing AI solutions: identity, keys and networking; 3. Operating AI solutions: quotas, monitoring, evaluation and CI/CD |
| Manage, monitor, and secure AI systems | 2. Securing AI solutions: identity, keys and networking; 3. Operating AI solutions: quotas, monitoring, evaluation and CI/CD; 12. Azure AI Search and retrieval-augmented generation |
| Implement responsible AI across generative AI and agentic systems | 3. Operating AI solutions: quotas, monitoring, evaluation and CI/CD; 4. Responsible AI, guardrails and Azure AI Content Safety |
| Implement generative AI and agentic solutions (30–35%) | |
| Build generative applications by using Foundry | 1. Microsoft Foundry: models, resources and deployments; 3. Operating AI solutions: quotas, monitoring, evaluation and CI/CD; 5. Building generative applications: prompts, parameters and quality; 6. Building agents with Foundry Agent Service; 7. Image and video generation and multimodal understanding; 12. Azure AI Search and retrieval-augmented generation |
| Build agents by using Foundry | 3. Operating AI solutions: quotas, monitoring, evaluation and CI/CD; 4. Responsible AI, guardrails and Azure AI Content Safety; 5. Building generative applications: prompts, parameters and quality; 6. Building agents with Foundry Agent Service |
| Optimize and operationalize generative AI systems | 3. Operating AI solutions: quotas, monitoring, evaluation and CI/CD; 5. Building generative applications: prompts, parameters and quality; 6. Building agents with Foundry Agent Service |
| Implement computer vision solutions (10–15%) | |
| Design and implement image- and video-generation solutions | 7. Image and video generation and multimodal understanding |
| Design and implement multimodal understanding workflows | 7. Image and video generation and multimodal understanding; 8. Azure Vision: image analysis and OCR; 13. Document and content extraction |
| Implement responsible AI for multimodal content | 7. Image and video generation and multimodal understanding |
| Implement text analysis solutions (10–15%) | |
| Apply language model text analysis | 4. Responsible AI, guardrails and Azure AI Content Safety; 9. Text analysis with Azure Language and language models; 10. Translation: text, documents and speech |
| Implement speech solutions | 10. Translation: text, documents and speech; 11. Speech and voice agents |
| Implement information extraction solutions (10–15%) | |
| Build retrieval and grounding pipelines | 5. Building generative applications: prompts, parameters and quality; 8. Azure Vision: image analysis and OCR; 12. Azure AI Search and retrieval-augmented generation; 13. Document and content extraction |
| Extract content from documents | 13. Document and content extraction |
The full list of tasks under each objective is in Microsoft's official study guide. The book is organised by technology, so one chapter often serves several objectives.