Paper rules break first
Two months of running the agent-team starter prompt taught me which rules actually hold. The ones wired into tooling survived. The ones that only lived in prose were the first to e...
Tagged: workflow
All
AI Engineering
3D Printing & Making
Tools & Workflow
LLM Patterns
Career & Thinking
Infrastructure
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...
I was the validator all along
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.
A starter prompt that actually remembers what you told it
I rebuilt my Claude Code starter prompt around .md files as external memory. Here's why and how.
Context hygiene: why your AI forgets what matters and what to do about it
The biggest bottleneck in long-running AI sessions isn't model intelligence — it's context management. Here's what I've learned about keeping AI on track across complex, multi-sess...
Claude Code's /memory is one-fifth of a context management system
Claude Code has a `/memory` command that appends facts, preferences, and constraints to a `CLAUDE.md` file — either global (`~/.claude/CLAUDE.md`) or project-l...
Markdown files as CMS: the LLM-friendly approach
Using markdown files in git as your content management system turns out to be the most LLM-friendly publishing workflow I've found. Any AI assistant that can...