Tag
Guardrails
5 posts filed under Guardrails.
Groundedness Detection vs Groundedness Evaluation: Two Azure Products, One Name
Azure has two features named Groundedness — a runtime detection API that blocks ungrounded answers, and an offline evaluator that scores them in CI.
The Production Guardrail Stack: Presidio + Azure Content Safety + NeMo Guardrails Around a MAF Agent
How to compose PII redaction (Presidio), Azure AI Content Safety, and NeMo Guardrails as layered middleware around a Microsoft Agent Framework agent.
Defense-in-Depth for AI Agents on Azure: Prompt Shields, Spotlighting, and the Coverage Gap
What Azure's Prompt Shields and Spotlighting actually block against jailbreaks and prompt injection — and the gap: they don't fire on agent tool calls.
Microsoft Agent Framework Makes Tool and File Access Approval-by-Default
Agent Framework Python 1.10.0 and .NET 1.12.0 flip skill and file access to approval-required by default — a breaking change for production MAF agents.
AI Security: Prompt Injection, Jailbreaks, and Guardrails
Prompt injection, indirect injection, jailbreaks, and data exfiltration via tools — the real threats and defense layers that work in production AI systems.
