https://hapdo.io/research/ Notes on what happens to software security when agents write the code. en https://hapdo.io/research/agents-permissions-security-boundary/ https://hapdo.io/research/agents-permissions-security-boundary/ Thu, 03 Sep 2026 12:00:00 GMT An agent’s model is only one part of its risk. Identity, credentials, tools, network access, workspace, and execution policy define what it can do. https://hapdo.io/research/ai-changes-the-pace/ https://hapdo.io/research/ai-changes-the-pace/ Sun, 30 Aug 2026 12:00:00 GMT AI changes how fast we build, not who owns the result. Agent-written code still needs evidence, review, and clear human accountability.