Blog
Thoughts, notes & the occasional deep dive.
11 October 2026
If OpenAI Couldn't Control Its Own AI Agent, Can You Manage the Risk?
The real question is not whether your AI agent can act autonomously. It is whether your organisation has built the controls to constrain, observe and intervene when it does. An architect's way to decide how much authority an agent should get.
22 September 2026
If Tokens Are Getting Cheaper, Why Are AI Agent Bills Going Up?
What tokens are, why AI agents use far more of them than chat, and why falling token prices have not made agent bills smaller.