◆ read · latest writing
What's going up, week by week.
Playbooks, primers, wire dispatches, tactics, and signal — every piece on the site, newest first. The five formats stay separate when you want to browse by intent; here's what each one is for.
- PLAYBOOKArchitecture9 min read
Choosing between RAG, MCP, and both.
The RAG-or-MCP question collapses into three architectural questions about what your system reads, acts on, and how it answers. Five worked use cases show what the picks look like.
- PRIMERPattern6 min read
MCP vs RAG.
The comparison is misframed. MCP is a tool-call protocol; RAG is a retrieval pattern. Most real systems run both, at different layers of the stack.
- PLAYBOOKArchitecture9 min read
How to build a custom MCP in your app.
An opinionated playbook for the in-app HTTP MCP pattern. Build it once inside your existing TypeScript app, and it pays back twice: at the keyboard interactively, and on a schedule via Routines.
- WIRERelease5 min read
Anthropic ships Routines.
Claude Code can now run scheduled agents on Anthropic's infrastructure with your MCPs and skills wired in. The piece that was missing for end-to-end automation without a separate cron worker.
- PLAYBOOKWorkflow9 min read
The Charlie Hills LinkedIn stack.
One voice profile, eighteen skills, every channel downstream of a single newsletter.
- PLAYBOOKArchitecture8 min read
How to build an AI agent.
Why most agent projects fail at step one, and what the eight-step process actually buys you when you take it seriously.
- WIREIndustry5 min read
The CLI agent wars settle into a pattern.
Claude Code, Codex, Aider, and Cursor's terminal mode have converged on the same shape. The convergence tells us what is coming next.
- TACTICSPrompting
Lead with the stack.
State your framework, runtime, and hard constraints in the first line of the prompt. Do not bury them.
- SIGNALTalk
Software 3.0.
via Andrej Karpathy
Andrej Karpathy reframes the last three decades of programming as three software paradigms, and puts vibe coding in a longer arc.
- PRIMERPattern7 min read
Building effective agents.
Anthropic's quiet thesis. Most AI features do not need an agent, and the ones that do follow a smaller pattern than the framework discourse suggests.
◆ browse by format