Securing Agent-to-Agent (A2A) Communication
Securing agent-to-agent communication has become one of the harder problems in enterprise AI, because multi-agent systems are being deployed faster than their…
FIELD NOTES · 2026 EDITION
Blogs
714 posts on cloud, security, DevOps and AI.
AI Agents as the New Insider Threat
For thirty years, insider threat programs have been built around a single assumption: the insider is a person. A person can be…
Microsoft Entra Agent ID Setup Guide
AI agents now act inside tenants with the same reach as employees, yet most were stood up as ad-hoc service principals with…
OWASP Top 10 for Agentic Applications
Security teams that spent two years hardening chatbots are now staring at a different problem. The OWASP Top 10 for Agentic Applications,…
Zero Trust for AI Agents in the Cloud
As a security professional who spends most working weeks inside Azure tenants watching automation scale past the point where any human reviews…
Australia Horizon 2 Cyber Strategy
As a security architect working across Australian regulated environments, I have watched the 2023-2030 Australian Cyber Security Strategy move from foundation-setting to…
Non-Human Identity Sprawl
Most security programs were built to protect people. Single sign-on, multi-factor authentication, privileged access management, and quarterly access reviews all assume an…
Wiz vs Microsoft Defender for Cloud
After running cloud security posture programmes across a range of organisations, I get asked the wiz vs microsoft defender for cloud question almost every…
Best Practices to Prevent Prompt Injection Attacks
In June 2025, researchers at Aim Security disclosed EchoLeak, a zero-click vulnerability in Microsoft 365 Copilot tracked as CVE-2025-32711. A single crafted…
Tata Electronics Supply Chain Breach: Apple and Tesla
As a security professional who spends most days inside the third-party risk programmes of regulated Australian organisations, I read the Tata Electronics…