My .md files vs Claude's memory tool: a practitioner comparison
Anthropic shipped a memory tool that looks structurally identical to the markdown files I've been maintaining by hand. Here's what each approach gets right, where they diverge, and...
Anthropic shipped a memory tool that looks structurally identical to the markdown files I've been maintaining by hand. Here's what each approach gets right, where they diverge, and...
I've been writing about context management at the individual and team level. This post zooms out: if context is the real bottleneck in AI, who owns it across an organization — and...
We've been solving the 'too complex for one person' problem for decades in program delivery. Now some team members are language models — and the coordination overhead is measured i...
Six years ago I helped a CPG company dream up a smart meal planner. We never shipped it. This year, my wife and I built it — and we use it every week.
Running three AI agents sounds expensive. It's cheaper than running one — if you put the right model in each role.
Splitting a single AI agent into a team didn't just change the workflow — it changed how context flows through the whole system.
My AI coding setup worked — until I noticed I was spending more time checking output than building. The fix was giving the validation job to another agent.
The tedious work of program management was never just overhead. It was also how we learned the craft. AI is automating that path — and nobody's talking about what replaces it.
The manual context management patterns that work today map surprisingly well to the agent memory architectures being built for tomorrow.
I rebuilt my Claude Code starter prompt around .md files as external memory. Here's why and how.