New Mac setup for AI developers in 2026 (the apps I install on day 1)
Just unboxed a new Mac and going to do AI dev work? The 15 apps I install before doing anything else — with one-liner brew installs.
How AI multi-taskers organize files, projects, and prompts on macOS — plus deep-dives into the engineering behind mq-dir.
Just unboxed a new Mac and going to do AI dev work? The 15 apps I install before doing anything else — with one-liner brew installs.
Dual-pane is still the right shape for most copy/move workflows. Here's the 2026 round-up of the four serious contenders, plus when to outgrow them.
Local LLMs got dramatically better in 2025-2026. They're competitive with frontier APIs for some workflows; not all. Here's the honest picture.
Sometimes an agent goes way past scope and modifies things it shouldn't have. Here's the rollback playbook — git-based, fast, low-stress.
Terminal file managers are having a renaissance in 2026, led by Yazi's Rust-built async engine. Here's the honest comparison of the four serious contenders.
Claude Code's memory feature is powerful but easy to misuse. The pattern that scales — what to put in global memory, what to put per-project, what to never persist.
AI agents produce diffs that look right and are subtly wrong. Here's the structured review checklist that catches the drift before it ships.
AI dev workflows put unusual demands on file management — parallel agents, generated artifacts, fast iteration. Here are the seven file managers worth your attention in 2026, ranked by fit.
When an AI agent has access to your whole repo, it doesn't read your whole repo. Here's how to choose what enters context, what stays out, and how that decision affects output quality.
v0.1 shipped. Here's what we're working on for v0.2 — and why we're deliberately not shipping AI features inside the app, despite the obvious temptation.
AI agents fail in specific ways. The right debugging response depends on the failure mode. Here's the structured protocol that catches drift fast.
Five parallel agents produce a lot of output. The trick is summarizing what mattered without reading every commit. Here's the daily routine.