What’s new in Azure Language in Foundry Tools

2026-05-30 · Source: Microsoft Foundry Blog articles · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Cybersecurity & Data Privacy, Software Development & Engineering · Depth: Intermediate, short

Summary

Microsoft announced significant updates to Azure Language in Foundry Tools at Microsoft Build, enhancing capabilities for identifying and managing sensitive information across text, conversations, and healthcare scenarios. Key releases include a generally available (GA) Text PII API (2026-05-01) with advanced redaction options like "syntheticReplacement" for anonymization, optional type validation controls, and configurable confidence thresholds. New preview releases for Text PII and Conversational PII expand entity detection to include items like Password, PIN code, Zip code, Airport code, GitHub account identifiers, and credit card expiration dates. Additionally, Microsoft introduced Foundry playgrounds for Text PII, Conversational PII, and Text Analytics for Health, allowing teams to explore and evaluate API functionalities before integration. These updates aim to automate privacy protection and streamline data processing for various application workflows.

Key takeaway

For AI Engineers or Data Privacy Officers building applications that handle sensitive information, these Azure Language in Foundry Tools updates offer critical capabilities. You can now automate PII detection and redaction more precisely using the GA Text PII API's new customization features, including "syntheticReplacement" for anonymization. Utilize the new Microsoft Foundry playgrounds to thoroughly evaluate API performance and integration suitability before deploying privacy-aware solutions, ensuring compliance and data integrity.

Key insights

Azure Language in Foundry Tools now offers enhanced PII detection and redaction with new APIs and interactive playgrounds.

Principles

• Automate privacy protection.
• Tailor PII processing.
• Evaluate APIs pre-production.

Method

The GA Text PII API allows configuring anonymization via "syntheticReplacement", disabling entity type validation, and setting confidence score thresholds for output control.

In practice

• Use "syntheticReplacement" for anonymization.
• Explore Foundry playgrounds for testing.
• Configure confidence thresholds.

Topics

• Azure Language
• PII Detection
• Data Redaction
• Text Analytics for Health
• Conversational AI
• Microsoft Foundry

Best for: CTO, AI Architect, Machine Learning Engineer, AI Engineer, Software Engineer, AI Security Engineer

Related on AIssential

• Building Ambient AI Medical Scribes: Best Practices — Accurate, private, and context-aware transcription is critical for effective AI medical scribes.
• OpenAI Open-Sources Privacy Filter, a Tiny Model That Scrubs PII Without an API Call — Privacy Filter offers local, context-aware PII detection with high efficiency and fine-tuning capabilities.
• New Azure Open AI models bring fast, expressive, and real‑time AI experiences in Microsoft Foundry — New Azure OpenAI models prioritize continuity and reliability for complex, real-time AI applications and long-running engineering tasks.
• AI chatbots are giving out people’s real phone numbers — Generative AI chatbots frequently expose personal data, primarily due to PII in training sets, with limited user recourse.
• "Not Available in Your Region" Isn't a Dead End: A Security Assessment of Global Deployments — Microsoft Foundry Global deployments provide secure, compliant access to new AI models with data residency guarantees.
• How to build scalable web apps with OpenAI's Privacy Filter — OpenAI's Privacy Filter is an open-source PII detector enabling scalable, custom web applications via `gradio.Server`.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Microsoft Foundry Blog articles.