Evaluation & Safety
Implement content filtering, prompt shields, adversarial testing, and responsible AI governance. Part of the free Azure AI Foundry — every lesson below is open to everyone, no signup required.
// LESSONS IN THIS MODULE
- 01Content Filtering & Prompt Shields9 min · 80 XP
Automated Safety Guards Azure AI Foundry provides multi-layered content safety powered by Azure AI Content Safety : Content Filter Categories Category...
- 02Adversarial Testing & Red Teaming9 min · 80 XP
Stress-Testing Your AI Foundry's Adversarial Simulation generates attack datasets to test your application's resilience before deployment. The Respons...
- 03ASSERT Framework & Agent Control10 min · 90 XP
Automated Agent Testing The ASSERT Framework (Automated Safety & Security Evaluation for Responsible Testing) is Microsoft's approach to systematicall...
- 04Enterprise Governance & Security12 min · 150 XP
Securing Agent Deployments As agents gain autonomy, security transitions from static checks to runtime evaluation. Microsoft Foundry provides comprehe...