Azure AI Studio

Bias Factuality Groundedness Hallucination Privacy Robustness Safety Toxicity

Data Exfiltration Jailbreaks Model Misuse Prompt Injection Prompt Leaking

Automated Red Teaming Continuous Testing Human Red Teaming Playground Testing Safety Evaluations Scenario Libraries

Audit Trails Content Moderation Governance Guardrails Policy Enforcement Risk Assessment

Agents Chatbots LLMs Multimodal RAG Vision

Azure Hybrid Cloud On-premises Private Link SaaS

Azure OpenAI LangChain LlamaIndex Microsoft Purview Teams

FedRAMP GDPR HIPAA ISO 27001 SOC 2

Alerts Dashboards Explainability Metrics Notebooks Reports