AI-103 skill area 3 of 5 · exam weight 10–15%

Implement computer vision solutions

Generating and editing images and video, multimodal understanding with Content Understanding, and responsible AI for visual content.

Implement computer vision solutions is worth 10–15% of the AI-103 exam. The study guide divides it into three skill groups: designing and implementing image- and video-generation solutions, designing and implementing multimodal understanding workflows, and implementing responsible AI for multimodal content.

On the generation side, the guide lists generating images and videos from text prompts and reference media, configuring image-editing workflows such as inpainting, mask-based edits and prompt-driven modifications, implementing workflows to edit generated videos, and selecting the generation and editing controls the platform provides.

Multimodal understanding is the biggest group in the area. It covers analyzing visual context with multimodal models, producing concise or detailed captions for one or more images, question answering grounded in visual evidence, generating alt text and extended image descriptions aligned to accessibility guidelines, configuring Azure Content Understanding in Foundry Tools to extract visual characteristics, video analysis workflows that process and interpret video segments, single-task and pro-mode Content Understanding pipelines, and identifying objects, components or regions within images or video.

Responsible AI for multimodal content covers filters that classify unsafe or disallowed visual content, detecting and mitigating indirect prompt injection that uses text embedded in images, and enforcing visual policy rules such as applying watermarks, flagging prohibited symbols, upholding brand usage requirements and detecting potentially inappropriate content.

Source: Microsoft's AI-103 study guide (skills measured as of April 16, 2026). Documentation: Azure Content Understanding documentation, Azure AI Vision documentation.

33 practice questions in this area, covering 16 of 16 study-guide skills.