[The Null Hypothesis]

Recent Posts

Testing in the Age of AI Agents

When code changes at the speed of thought, tests become less about verification and more about defining what should remain stable. A philosophy for testing when AI agents write and rewrite your code.

How My Agent Learned GitLab

Teaching an agent to use CLI tools isn't about writing perfect documentation. It's about creating a feedback loop where the tool teaches, the agent learns, and reflection builds institutional knowledge.

When CLI Tools Are Enough

One year after MCP's launch, Anthropic published a solution to context overhead: filesystem-based tool discovery. The pattern looked familiar.