Stay Safe Out There: Build Security In
Security is strongest when it is built into every boundary, permission, and design decision instead of added at the end.
Discover more
Procedural Memory and Skills: Teaching Agents Reusable Ways to Work
Procedural memory is not about facts or chat history. It is the reusable method an agent follows to complete recurring tasks. This article explains why skills matter, how they work, and why they make agents behave more like software systems than chat systems.
Property-Based Testing: Test the Rules, Not Just the Examples
Property-based testing moves beyond hand-picked examples by testing the rules that should remain true across many possible inputs.
Refactoring: Improve Continuously, Not Occasionally
Tests do more than catch defects. They document behaviour and give developers the confidence to change software safely.
Refactoring: Improve Continuously, Not Occasionally
Every file you touch gives you a chance to make the next change easier.
Algorithm Speed: Solve the Right Problem First
The fastest code is rarely the most optimized. It is usually built on the right algorithm.
Programming by Coincidence: Make Every Line Intentional
Software that works without being understood is one refactor away from becoming tomorrow’s production bug.
Listen to Your Lizard Brain: Trust Your Instincts, Verify with Evidence
Your intuition is years of experience speaking quietly, but it still needs evidence before it becomes knowledge.
AI Agent Memory: Why State and Memory Are Not the Same Thing
State keeps an agent moving through the current thread. Memory persists selective information for future runs. External knowledge stays in source systems and should be retrieved on demand. This distinction matters because AI agent memory is a systems design problem, not a prompt trick.
Shared State Is Incorrect State: Reduce Hidden Dependencies
The most difficult bugs often come from code that changes data you did not realize it could touch.