Blog
Steering and checking agents
Practical posts for teams working with AI agents such as Claude Code: one documented risk, one example and steps to check your configuration yourself.
10 November 2026
57% correct, 11.8% secure: why working agent code is not secure code
The tests are green and the feature works. A recent study shows why, for code written by AI agents, that says little about security.
3 November 2026
Steering competence: the AI skill nobody teaches
Your team can operate Claude Code or Codex. But can it also steer and control its agents? Five questions and a self-check.