Ken Muse

Ever spent time carefully documenting your project’s folder structure in a copilot-instructions.md file? You’re not alone – it’s one of the most common things developers add. But here’s the thing: VS Code’s Copilot extension already injects a workspace tree into every conversation automatically. And when that tree gets truncated, the LLM has tools to explore further on its own. In this post, I’ll show you what’s happening under the hood so you can spend those instruction tokens on things that genuinely matter.

Every conversation with AI starts from scratch – no memory of yesterday’s debugging session, your team’s naming conventions, or the architectural decision you patiently explained three times last week. Agentic memory changes that. It gives AI assistants the ability to accumulate knowledge over time, turning them from stateless tools into collaborators that genuinely improve. In this post, I’ll walk you through the different types of memory and show you how VS Code and GitHub Copilot put these ideas into practice today.

Have you ever tried to ask the AI to create multiple subagents? Or seen an agent that explicitly requests multiple subagents do the same task? The mechanics behind that pattern are more interesting than they appear. In this post, I’ll show you why this pattern works so well – from cleaner context and richer coverage to stronger critique loops – so you can decide when it is worth using in your own workflow.

When the axios npm library was compromised in March 2026, it reminded me that the dependencies we trust every day can turn on us without warning. That got me thinking – what about the extensions running in my IDE? They auto-update silently, they have access to my filesystem and credentials, and I never review the changes. If you’ve ever updated a tool without a second thought, this post is for you.

Rootless Docker sounds like the perfect answer to container security – no more root daemon, no more worry. If you look at how it actually works under the hood, the story is more nuanced than most teams realize. In this post, I walk through user namespaces and UID mapping, dig into why kernel developers have concerns about the attack surface, and explain what you’re actually giving up when you enable rootless and set seccomp=unconfined and apparmor=unconfined.

Ever wondered what’s really happening when Docker runs your containers? It turns out the daemon needs some serious privileges to do its job. I wrote this post to trace the path from the Docker daemon through the Unix socket, image builds, and BuildKit – showing you exactly where root access comes into play and why every step depends on it.

Ever wondered why Docker commands need sudo or docker group membership? The answer is baked into the Linux kernel itself. I wrote this post to peel back the curtain on what a container actually is. You’ll recreate container-style process isolation from scratch using standard command-line tools – building your own namespaces and cgroups by hand to see exactly what’s happening under the hood.

If you’ve ever adjusted an AI temperature slider without really knowing what it does, you’re not alone. These settings appear across AI tools and model APIs, but the actual mechanics rarely come with a clear explanation beyond “higher is more creative.” I wrote this post to change that. In it, I break down how Large Language Models select their next word, walk through the math behind softmax, and explain how temperature, Top-K, Top-P, and Min-P each shape the output – so you can tune these settings with confidence instead of guessing.

Ever wish you could run multiple Copilot CLI agents at once without turning your repo into chaos? I ran into that exact challenge while trying to juggle parallel tasks. I’ll show you when to use workspace versus worktree isolation, how to review and merge agent changes safely, and how to clean up so your workflow stays fast and tidy.

You’ve heard that custom agents and multi-agent workflows produce better results from AI coding assistants – but do you know why? The answer isn’t just about organization. It’s about a fundamental constraint baked into every large language model: the context window. Understanding how tokens, context, and tools interact can save you hours of frustration. Let me walk you through the mechanics.