Secure architecture for the age of AI
AI security architecture for the age of AI agents
Helping organizations capture the business value of AI without taking on unacceptable risk. Practical, vendor-neutral AI security architecture for securing AI agents, MCP and agentic workflows, from threat models and reference architectures to governance in production.
Agentic AI security, end to end
Secure AI Architecture
Reference architectures for LLM applications, RAG pipelines, MCP gateways and agentic workflows: identity, data boundaries, guardrails and isolation.
AI Threat Modeling
Prompt injection, data poisoning, model supply chain and tool abuse, mapped to controls architects can actually deploy.
AI Governance & Strategy
Turning frameworks like NIST AI RMF, ISO/IEC 42001 and the EU AI Act into architecture decisions and roadmaps.
Latest AI security articles
All articles
AI Governance That Actually Works: If You Can't Enforce It, It Isn't Governance
Here’s a question I’d put to any board that has signed off an AI policy: “If an AI agent broke that policy this afternoon, how would we know, and what would stop it?”
Read More
Agent-to-Agent (A2A) Security: Discovery Is Not Authorization
When one of your AI agents asks another agent for help, how does it know that agent is who it claims to be? In most early deployments, it doesn’t. It found the other agent in a directory, read a description the other agent wrote about itself, and started sending it data.
Read More
An Internal AI Marketplace Without the Supply Chain Risk
Here’s a question every CISO will be asked within the next year: “Can we set up an internal AI marketplace so teams can share AI agents and tools?” The right answer is yes. The wrong way to deliver it is as an app store with no inspection.
Read MoreBuilding the hub for AI security architects
This site starts as a blog and is growing into a home for the whole community. Here’s what’s coming.
Architecture library
Curated reference architectures, patterns and control mappings.
Coming soonJob board
AI security architecture roles from teams that take it seriously.
Coming soonArchitect network
A directory of practitioners to learn from, hire and collaborate with.
Coming soonStrategy sessions
One-to-one sessions to pressure-test your AI security architecture.
Coming soonPressure-test your AI security architecture
Book a strategy session to review your AI threat model, reference architecture or governance roadmap with an experienced security architect.
Book a strategy session