Welcome to AI Security Architects

Welcome to AI Security Architects

Table of Contents

AI systems are moving from experiments to production faster than most security architectures can adapt. Models call tools, agents act with real credentials, and sensitive data flows through retrieval pipelines that did not exist a year ago. AI Security Architects is a place to work through what secure design looks like in that world.

What this blog will cover

  • Reference architectures for LLM applications, retrieval-augmented generation (RAG) and agentic systems.
  • Threat modeling for AI: prompt injection, data poisoning, model and dependency supply chain risk, and excessive agency.
  • Identity and data boundaries for AI workloads: who (or what) is acting, and on whose behalf.
  • Governance in practice: turning frameworks such as the NIST AI RMF, ISO/IEC 42001 and the EU AI Act into architecture decisions.

Where it’s heading

This starts as a blog. Over time it will grow into a hub for the AI security architecture community, with a library of patterns, a job board, a directory of architects, and bookable strategy sessions.

If there’s a topic you want covered, or you’d like to pressure-test your own architecture, get in touch.

Share :