Concept Template

James Phoenix

James Phoenix

Use this template for each new concept. Copy and rename.

Definition

[One-sentence definition]

Mental Model

[Analogy or intuition that makes it click]

Read The Meta-Engineer

A practical book on building autonomous AI systems with Claude Code, context engineering, verification loops, and production harnesses.

Continuously updated

Claude Code + agentic systems

Code Example

// Minimal working example

Where I Used It

[Project or experiment where this concept was applied]

Gotchas

[Common mistakes or misconceptions]

Related Concepts

Related Concept

Sources

[Book, article, or documentation link]

Template Usage

Copy this file to concepts/[concept-name].md
Replace bracketed sections with actual content
Link from relevant roadmaps and projects
Update when you gain new insights

Explore it visually

Newsletter

Become a better AI engineer

Weekly deep dives on production AI systems, context engineering, and the patterns that compound. No fluff, no tutorials. Just what works.

Join 306K+ developers. No spam. Unsubscribe anytime.

More Insights

Cover Image for Build Features in the CLI Before the API

Build Features in the CLI Before the API

September 22, 2026

Make the next app as much of a CLI app as possible. Feature work happens in the terminal, in-process, against the real development database. The HTTP API is a thin adapter you add afterwards, and a lint rule fails CI if it ever gets a route the CLI does not have.

James Phoenix

Cover Image for Useful Output Across Three Modes of Work

Useful Output Across Three Modes of Work

September 16, 2026

I compare typing, interactive AI assistance, and automated loops by useful output per hour of my attention, including review, compute, and failure costs.

James Phoenix