AI Security reference architecture
LLM governance
Inventory, risk tiers, approved providers and review gates for enterprise use of language models.
Design principles
- Know every AI system in use
- Tier systems by risk
- Approve providers and models centrally
- Review before launch, monitor after
Components
| Component | Role |
|---|---|
| AI inventory | Systems, owners, data |
| Risk tiers | Controls proportional to risk |
| Usage policy | What may be sent where |
| Review board | Launch approvals |
More AI Security architectures
AI security architecture
A security layer between applications and models covering prompts, data, agents, MCP and policy.
View architectureMCP security
Identity, authorization, inspection and audit for agents calling tools through Model Context Protocol servers.
View architectureAI agent security
Scoped permissions, approvals and monitoring for autonomous and semi-autonomous agents.
View architectureAdapt this to your environment
We'll help you apply this pattern to your constraints and existing estate.

