Posts

All the articles I've posted.

• AI Agents Need Identity: Why Non-Human Access Is the Next Security Frontier

  Published:Apr 18, 2026 |  at 02:00 AM

  Agentic AI is dramatically expanding the population of non-human identities with persistent privileges, limited visibility, and unclear ownership. This article explains why agents, service accounts, bots, and API clients now require the same rigorous identity lifecycle management as human users.

• AI Coding Agents Are Productive, but Who Owns the Review Debt?

  Published:Apr 17, 2026 |  at 08:20 AM

  AI coding agents are increasing development velocity, but they also create a new form of review debt. The real management question is not how much code agents write, but who is accountable for proving it is safe.

• MCP Security Debt: Why Enterprise AI Connectors Need a No-Go Zone

  Published:Apr 16, 2026 |  at 07:35 AM

  As enterprises connect AI agents to internal tools, MCP-style integrations create a new class of security debt. The real risk is not the model; it is what the model is allowed to touch.