Posts by Blake Bailey on building AI agents that are safe to run, and on testing them.https://blakells.dev/https://blakells.dev/writing/enforcing-dry-runs-in-the-browser/https://blakells.dev/writing/enforcing-dry-runs-in-the-browser/Why a prompt that says "don't submit" is not enough, and the guard, hook and audit that make Preflight's dry runs hold.Tue, 10 Nov 2026 00:00:00 GMThttps://blakells.dev/writing/testing-an-agent-that-must-never-submit/https://blakells.dev/writing/testing-an-agent-that-must-never-submit/How Preflight's test suite proves its dry-run guard works, with a fake LLM, real Chromium and requests that never arrive.Tue, 10 Nov 2026 00:00:00 GMT