What Is Agent Orchestration? A Practical Guide
What is agent orchestration? Learn how AI agent orchestration coordinates multi-agent workflows with clear roles, handoffs, and specs.
Blog
Guides on agent orchestration, working directories, and building portable agentic systems.
OpenCode vs Claude Code: A Side-by-Side Comparison
OpenCode vs Claude Code — compare directory structures, agent formats, and configuration to pick the right coding agent for your workflow.
Working Directories for AI Agents: A Practical Guide
Learn how to set up working directories for AI agents with real examples, directory layouts, and patterns that make agent workflows repeatable.
What Is CLAUDE.md and How to Write One
CLAUDE.md is the main instruction file for Claude Code. Learn what goes in it, see a practical template, and understand the 200-line rule.
AGENTS.md Guide: Configure OpenCode Like a Pro
Learn how to write an AGENTS.md file to configure OpenCode. Practical examples, format breakdown, and comparison with CLAUDE.md for Claude Code.
The Complete Guide to Claude Code Directory Structure
Learn how the .claude/ directory structure works in Claude Code. Explore agents, skills, rules, hooks, and configuration files.
What Is an Agent Harness? The Infrastructure Layer Behind Every AI Agent
An agent harness manages context, tools, permissions, and memory for AI agents. Learn what it is, why it matters more than the model, and how to avoid lock-in.
Agentic System Architecture: Patterns for Multi-Agent Workflows
How to architect an agentic system with defined agent roles, orchestration patterns, and shared state. Covers sequential, parallel, hub-and-spoke, and hierarchical delegation.
Agent Memory Ownership: Why File-Based Memory Beats API Lock-In
Your AI agent accumulates valuable project knowledge across sessions. Where that memory lives determines whether you own it or rent it. A guide to portable agent memory.
Claude Code settings.json: Every Option Explained
The complete guide to Claude Code settings.json. Learn how to configure permissions, hooks, environment variables, and model preferences.
Claude Code Hooks: A Practical Guide with Examples
Learn how to use Claude Code hooks to automate formatting, enforce rules, and control agent behavior with lifecycle events and shell commands.
How to Create Claude Code Skills: A Step-by-Step Guide
Learn how to create Claude Code skills — reusable instruction packages loaded via /slash commands. Includes SKILL.md format, examples, and best practices.
Claude Code Permissions: Allow, Deny, and Ask Patterns
Master Claude Code permissions with practical allow, deny, and ask patterns. Learn prefix matching, evaluation order, and production-ready examples.
Claude Code Rules: Scoped Instructions That Load Automatically
Learn how Claude Code rules work — scoped markdown instructions with path-glob matching that load only when relevant files are touched.
What Is CLAUDE.local.md and When to Use It
CLAUDE.local.md is your personal, gitignored instruction file for Claude Code. Learn when to use it, what goes in it, and how it works with CLAUDE.md.
Claude Code MCP Servers: Connect Any Tool via Model Context Protocol
Learn how to set up Claude Code MCP servers to connect your coding agent to GitHub, databases, and custom APIs via the Model Context Protocol.
Claude Code Subagents: When and How to Delegate Work
Learn how Claude Code subagents work — lightweight parallel workers that protect your context window and speed up research, review, and exploration.
Claude Code Agent Teams: Parallel Multi-Agent Orchestration
Set up Claude Code agent teams to coordinate multiple specialist agents working in parallel. Includes role definitions, patterns, and configuration.
Claude Code Context Window: How to Manage It for Better Results
Learn how the Claude Code context window works and practical techniques to manage it — from /clear habits to subagent delegation and project structure.
Claude Code Best Practices for Production Workflows
Practical Claude Code best practices — from /clear habits and hook setup to permission patterns and multi-agent project structure.
Spec-Driven Development: Write the Spec, Then Let Agents Build
Spec-driven development turns markdown specifications into the source of truth for AI coding agents. Learn the format, workflow, and templates.
Cursor vs Claude Code: Which AI Coding Tool Should You Use?
Cursor vs Claude Code — compare the AI-powered IDE against the terminal coding agent. Architecture, features, pricing, and when to use each.
Aider vs Claude Code: Cost, Workflow, and Setup Compared
Aider vs Claude Code — compare the lightweight pair programmer against the full coding agent. Token efficiency, multi-model support, and feature depth.
How to Set Up an AI Coding Agent From Scratch
Complete beginner guide to setting up an AI coding agent. Covers instruction files, permissions, project structure, and automation hooks.
How to Write Effective AI Agent Instructions
Learn how to write AI agent instructions that produce consistent results. Covers specificity, scoping, the 200-line rule, and cross-platform tips.
AI Agent Workflow Patterns: Sequential, Parallel, and Beyond
The five core AI agent workflow patterns — sequential pipeline, parallel fan-out, hierarchical delegation, hub-and-spoke, and feedback loop.
Claude Code Boilerplate: Templates and Starter Configs
Build a reusable Claude Code boilerplate with CLAUDE.md, settings.json, agents, rules, and skills. Includes templates by project type.
Claude Code for Teams: Shared Configuration Patterns
Set up Claude Code for teams with shared CLAUDE.md, permissions, hooks, and rules — plus personal overrides that never conflict.
How to Write a CLAUDE.md That Actually Works
Practical guide to writing CLAUDE.md files that make Claude Code sessions productive from the first prompt. Includes the 5 essentials and testing tips.