WILL NESS

BLOG

Thoughts on AI, development, and building products.

Use Subagents to Keep Your Context Window Small and Relevant
Coding Agents

Use Subagents to Keep Your Context Window Small and Relevant

Your coding agent performs best with a small, relevant context window. A mental model for using subagents (and skills) to engineer exactly what your agent sees, so it stays sharp.

·7 min read·Intermediate
claude-code
subagents
skills
+2
How to Get Your Coding Agent to One-Shot Complex Features
Coding Agents

How to Get Your Coding Agent to One-Shot Complex Features

My coding agent failed a complex Shopify integration, even after trying five times. Then I tried one thing differently, and it one-shotted the full feature. Here's the technique.

·5 min read·Intermediate
ai
coding-agents
productivity
+2
A Letter to the Developer Who Thinks AI Is a Gimmick
Coding Agents

A Letter to the Developer Who Thinks AI Is a Gimmick

AI is not magic - it's a pattern-matching tool. Understanding how LLMs work explains why your experience sucked and reveals when coding agents actually shine.

·10 min read·Beginner
ai
coding-agents
software-engineering
+1
Why You Need To Clear Your Coding Agent's Context Window
Coding Agents

Why You Need To Clear Your Coding Agent's Context Window

Why fresh context beats accumulated context for coding agents. Research on attention degradation and practical strategies for better AI-assisted development.

·5 min read·Beginner
ai
claude-code
context-window
+1
AskUserQuestionTool Changed How I Use Claude Code
Coding Agents

AskUserQuestionTool Changed How I Use Claude Code

Stop writing comprehensive prompts. Let Claude Code interview you instead. Here are 7 ways I use AskUserQuestionTool to improve my coding agent's output quality.

·5 min read·Beginner
claude-code
ai
productivity
+2
How to Run Multiple Claude Code Sessions at Once
Coding Agents

How to Run Multiple Claude Code Sessions at Once

Running multiple Claude Code sessions? Stop tab-hunting. This 5-minute tmux setup keeps every project organized in one place.

·3 min read·Intermediate
claude-code
tmux
productivity
+2
How To Get The Right Length Output From AI
General AI

How To Get The Right Length Output From AI

Use read time qualifiers like "make this a 3 minute read" instead of vague words like "concise" or "detailed" to control AI output length.

·3 min read·Beginner
ai
prompts
productivity
+2
Your Coding Agent Can Upgrade Itself
Coding Agents

Your Coding Agent Can Upgrade Itself

When your coding agent makes a mistake, use that moment to upgrade the agent, with the agent itself. One sentence, 30 seconds, permanent fix.

·4 min read·Intermediate
ai
coding-agents
productivity
+1
The Agentic Loop: Stop Babysitting Your Coding Agent
Coding Agents

The Agentic Loop: Stop Babysitting Your Coding Agent

The more your agent can run code and feed output back to itself, the less you do. Learn how to close feedback loops and let your coding agent iterate autonomously.

·4 min read·Intermediate
ai
coding-agents
productivity
+2
My Claude Code Workflow for Building Features
Coding Agents

My Claude Code Workflow for Building Features

A structured workflow for using Claude Code with sub-agents to catch issues, maintain code quality, and ship faster. Plan reviews, code reviews, and persistent task management.

·6 min read·Intermediate
ai
claude-code
workflow
+1
How to Actually Use AI (A Simple Framework)
General AI

How to Actually Use AI (A Simple Framework)

AI is a text predictor, not a mind reader. Structure your prompts with the RIPE framework (Role, Info, Process, Expected output) to get useful results instead of generic slop.

·8 min read·Beginner
ai
productivity
tutorial