AI-103 skill area 4 of 5 · exam weight 10–15%

Implement text analysis solutions

Language model text analysis (entities, summaries, sentiment, translation) and speech for agentic interactions.

Implement text analysis solutions is worth 10–15% of the AI-103 exam and has two skill groups in the study guide: applying language model text analysis, and implementing speech solutions.

Language model text analysis covers extracting entities, topics, summaries and structured JSON outputs by using generative prompting and Foundry Tools; configuring detection of sentiment, tone, safety issues and sensitive content; translating text with Azure Translator in Foundry Tools or LLM-powered translation flows; and customizing language model outputs for domain tasks such as compliance summarization and domain extraction.

Speech solutions cover converting speech to text and text to speech for agentic interactions, integrating speech as an agent modality (including custom speech models), enabling multimodal reasoning from audio inputs, and translating speech into other languages by using language models and Foundry Tools.

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

32 practice questions in this area, covering 8 of 8 study-guide skills.