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...
LLM Patterns
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...
More agents, less cost
Running three AI agents sounds expensive. It's cheaper than running one — if you put the right model in each role.
When one context window isn't enough
Splitting a single AI agent into a team didn't just change the workflow — it changed how context flows through the whole system.
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.
Your .md files are a memory architecture (you just don't call it that)
The manual context management patterns that work today map surprisingly well to the agent memory architectures being built for tomorrow.
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...
Starter prompt v2 for Claude Code agent teams, refined
Updated version of my Claude Code agent-teams starter prompt(/downloads/STARTPROMPT-AGENT-TEAMS-v2.md) after two months of running the previous cut on real p...
A starter prompt for Claude Code agent teams
I rebuilt my Claude Code starter prompt(/downloads/STARTPROMPT.md) for agent teams. The original positions Claude as a single project lead that both coordina...
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...
My Claude Code starter prompt with built-in context management
I published my Claude Code starter prompt as a downloadable file: STARTPROMPT.md(/downloads/STARTPROMPT.md) It sets Claude up as technical lead for any proj...