Azure AI Foundry
Managed AI platforms remove infrastructure work but keep every authorisation and data-boundary decision firmly on your side of the line.
Updated
How I use it
- Private networking and managed identity for inference endpoints
- Content filtering and abuse monitoring configuration
- Prompt and completion logging with bounded retention
- Model and deployment change control
Recurring problems I find
- API keys distributed to clients instead of a server-side gateway
- Default logging capturing personal data indefinitely
- Agent tools granted service-level rather than user-delegated permissions
Azure AI Foundry has been renamed Microsoft Foundry. Foundry Agent Service reached general availability with end-to-end private networking and OAuth Identity Passthrough for user-delegated tool access, and every Foundry agent now gets a Microsoft Entra Agent ID as its identity anchor.
Related
AI security
How to secure GenAI, LLM and agentic AI systems: current OWASP threat classes, layered controls, agent authority, retrieval isolation and monitoring.
LLM security controls
A control checklist for enterprise GenAI: data handling, retrieval isolation, agent authority, cascading-failure containment, monitoring, cost limits and vendor terms.
AI security assessment
Security assessment of GenAI and LLM systems: prompt injection, tool and agent abuse, data leakage, model supply chain and monitoring gaps.
STRIDE for AI systems
Applying STRIDE to LLM and agentic applications: what each category means when untrusted text can act as instructions, where STRIDE stops covering multi-agent failure modes, and the controls per element.
Prompt injection defence
Why prompt injection cannot be filtered away, why it has no full fix yet, and how to design AI systems — architecturally, not just with better prompts — so a successful injection has no useful consequence.
Three layers, three risk profiles
A security review that skips naming its layer — model, service, or agent — ends up testing the wrong attack surface.