Insights

Exploring technology, culture, and logic.

Series

Posts

The Coaching Habit: 7 Questions That Will Transform the Way You Lead

The Coaching Habit: 7 Questions That Will Transform the Way You Lead

What You Need to Know About Claude Code - 2026

What You Need to Know About Claude Code - 2026

Build Your Own Agent Harness: The Practical Blueprint (Part 12)

Build Your Own Agent Harness: The Practical Blueprint (Part 12)

Plan Mode: The Architecture of Thinking Before Acting (Part 11)

Plan Mode: The Architecture of Thinking Before Acting (Part 11)

Streaming Architecture: Building Agents That Feel Fast (Part 10)

Streaming Architecture: Building Agents That Feel Fast (Part 10)

Sub-Agents, Coordinators, and Skills: Multi-Agent Orchestration (Part 9)

Sub-Agents, Coordinators, and Skills: Multi-Agent Orchestration (Part 9)

The Hook System: Extension Points That Don't Break the Core (Part 8)

The Hook System: Extension Points That Don't Break the Core (Part 8)

Context Management: The Compression Problem (Part 7)

Context Management: The Compression Problem (Part 7)

The Memory System: How Agents Remember Across Sessions (Part 6)

The Memory System: How Agents Remember Across Sessions (Part 6)

Configuration as Architecture: The Multi-Layer Settings Problem (Part 5)

Configuration as Architecture: The Multi-Layer Settings Problem (Part 5)

The Permission Pipeline: Safety That Doesn't Get in the Way (Part 4)

The Permission Pipeline: Safety That Doesn't Get in the Way (Part 4)

The Tool System: How Agents Act on the World (Part 3)

The Tool System: How Agents Act on the World (Part 3)

The Dialog Loop: The Heartbeat of Every Autonomous Agent (Part 2)

The Dialog Loop: The Heartbeat of Every Autonomous Agent (Part 2)

What Is an Agent Harness? Why Your LLM Needs More Than an API Call (Part 1)

What Is an Agent Harness? Why Your LLM Needs More Than an API Call (Part 1)

Building a Travel Agent: Applying Claude Code's Design Patterns to a Real System

Building a Travel Agent: Applying Claude Code's Design Patterns to a Real System

How Claude Code's Safety Model Works (Part 6) — Patterns to Steal for Your Own Agentic System

How Claude Code's Safety Model Works (Part 6) — Patterns to Steal for Your Own Agentic System

How Claude Code's Extension System Works (Part 5) — Skills, Commands, and Subagents

How Claude Code's Extension System Works (Part 5) — Skills, Commands, and Subagents

How Claude Code's Memory System Works (Part 4) — What Agents Remember and Why It's Hard

How Claude Code's Memory System Works (Part 4) — What Agents Remember and Why It's Hard

How Claude Code's Tool Layer Works (Part 3) — Designing the Agent's Hands

How Claude Code's Tool Layer Works (Part 3) — Designing the Agent's Hands

How Claude Code's Master Loop Works (Part 2) — The Simple Pattern That Beats Complex Frameworks

How Claude Code's Master Loop Works (Part 2) — The Simple Pattern That Beats Complex Frameworks

How Claude Code's Architecture Works (Part 1) — 5 Layers You Can Steal for AI Agents

How Claude Code's Architecture Works (Part 1) — 5 Layers You Can Steal for AI Agents