Structure Files: Helping AI Navigate Your Codebase Without Getting Lost
Learn how structure files can help AI tools better understand and navigate your codebase, leading to more accurate and efficient AI-assisted development.
We’ve been promised a future where AI writes our code, fixes our bugs, and maybe even makes our coffee. But right now? Most of us are still spending way too much time explaining our codebases to AI assistants that seem to have the attention span of a caffeinated squirrel.
Let me paint a familiar scene: You ask your AI to add a new API endpoint. It responds by cheerfully rewriting your authentication system, completely missing your existing patterns, and somehow managing to reference a CSS file that hasn’t existed since 2019.
macOS Zoom Settings for Microphone
How I sound shouldn’t be a distraction if I’m talking with my colleagues on Zoom. I use a variety of microphones during the day. Built-in MacBook Pro, AirPods, and my trusty Shure SM7B dynamic microphone. Each microphone has its own sound and purpose. Sometimes it’s for high quality recordings or interviews, while other times for ease. Microphones are not the only variable, since location changes too. My team can tell you I call from coffee shops a number of times, which can be noisy depending on who ordered an espresso. My home office/bedroom doesn’t have much on the walls or floor, making it perfect for echoes. So while one microphone maybe good for one space, another one might be dreadful.
Language is key during incidents
“Cognitive load” is a term that refers to the amount of working memory resources someone can process at a given time. Working memory is a limited resource in capacity, related to how we learn and process information. If we have a lot of distractions (noise) or are constantly shifting tasks, it can impact our ability to learn. Why does this matter? During troubleshooting, people are actively trying to learn about what is happening in a system. They need to gather facts and understand what happened. Decisions need to be made. Depending on incident severity, the pressure to get things working can also be strong. Even more factors can be added, like if it’s their first on-call shift or if they think they are responsible for breaking the system. Whatever the factors, there’s a lot in an incident and that they compound against the troubleshooter’s ability to learn what’s happening. This is also why we need to ensure we’re not adding noise to an already noisy working memory of everyone involved. Ensure that the people in the room (real or virtual) don’t have diminished cognitive load and can stay focused on the problem.