Summary
Unit 7 of 7 · Module 16: Analyze text with Azure Language in Foundry Tools
Read this lesson
Three stops
Let's ride back through the module. Language detection names the language of each document, with its code and a confidence score. Entity recognition stamps the people, places, dates and organizations a text mentions. And PII detection finds personal details and hands you a redacted copy.
What to remember
Keep a few traps in mind. Use the resource endpoint, not the project endpoint. When you send one document, take result zero. Entity and PII requests take at most five documents, while language detection takes a thousand. And the redacted text is the safe copy to share, not the entity list. Next, you'll give these same skills to an agent, through the Azure Language MCP server.
Facts from Microsoft's documentation: What is Azure Language in Foundry Tools? (CC BY 4.0), rewritten in Loop's own words and examples. Narration, animation, and quiz by Loop. Microsoft, Azure, and Microsoft Foundry are trademarks of Microsoft. Loop is independent and not affiliated with or endorsed by Microsoft.