Today I used the term “brain vomit” in a meeting to describe what I’m doing in creating Copilot instruction files. I’ve used coding agents enough to know that while useful they have a tendency to use patterns I don’t immediately recognize and understand; or even like. I’m still just not comfortable giving agents large features to complete. I also personally find reusing common patterns and practices, whether solo or on a team, reduces overhead in reviewing, debugging, and making modifications. If you’ve ever had to work with many different teams with their own significantly different patterns and practices you’ll understand how much time gets wasted just trying to understand what you’re looking at. I’ve begun dumping (brain vomiting) my common preferred patterns and practices into instruction files. I structure my Lambda function files and the code within them in certain ways. I configure my DDB tables with a primary key named `pk` and sort key named `sk` while primary key values are prefixed with an item type. I almost never use the `Name` property on a resource in a CFN template. All of these are practices I developed for one reason or another and were often born out of lessons learned over time. To do this I started by using the Copilot CLI’s `/init` command in repos to generate instruction files based on the patterns the tool observes in my work. From there I’ve taken the instructions from the CLI’s output and used them to populate new instruction files targeted at specific technologies. (I prefer small topic based instruction files over large monolithic instruction files.) Next I’ve added more instructions based on memory or my own browsing through my projects. Finally I’ve been asking Copilot to suggest ways to simplify my instructions. My goal is to soon start creating coding agents with enough context that they are outputting code and building entire services in familiar looking ways. This lets me focus on evaluating how well the output functions and solves a problem rather than time spent figuring out how the output works and looking for subtle gotchas. Anyways, here’s the start of my collected patterns and practices. They’re mostly aimed at AWS serverless architectures. https://lnkd.in/esP6Jm5C #AWS #GitHub #Copilot
Josephe Beaudry
2mo
Check out https://yeoman.io/. Work with it to create common scaffolds. Then have it use yeoman to scaffold. Then you can rerun yeoman yourself on repos if you update the scaffold. Then you work with AI to manage templates that manage your code
Copilot instructions were so 2025 🤣 Just kidding, although it's been a while since I've used copilot. It always did a great job when I used it. I have to say though, I never used the CLI. I moved over to Claude just before OpenAI released Codex. I just feel like they were moving too slow and falling behind. Anyway, it's pretty much impossible to keep up with all the changes, and I'm spending every day working on various agentic workflows and trying my best to keep up with the daily and weekly changes.