Built with agents
One person, a coding agent, a shipped product: the real build logs, with the hours, the bills and the step that broke.
19 write-ups, newest first.
- Your AI Didn't Misread Your Code by Accident. You Handed It the Wrong Context.
- How to Turn the Workflows You Won't Document Into Agent Skills
- The AI Automation Ceiling: Why 60% Efficiency Doesn't Equal 20% Conversion
- Never Use a Model Where Code Can Decide
- Stop Using AI as a Chatbot: How to Build an Indie Workstation with Skills and Automation
- Stop Doing Manual DevOps: How I Use /loop and /hook to Automate My Daily Indie Hacker Tasks
- Best Practices for AI Agent Skill Management
- Stop Reading SimilarWeb Like a Traffic Dashboard — Read It Like a Feasibility Test
- Stop Chatting With AI: How I Use /loop and /hook to Automate My Indie Dev Workflow
- From AI Demo to Product: Loop Engineering for Indie Devs
- Why Pi's 1000-Token Agent Engine Needs a Sandbox Before You Touch It
- When AI Customer Service Backfired: Klarna’s Case and the Four-Stage Path to Enterprise AI Adoption
- AI Took Over My Coding. What Broke Was How I Learn.
- Sell It Before You Build It: How Indie Devs Validate AI Products
- Your Agent Writes Code Faster Than Anyone Can Review It
- The Klarna Lesson: Why AI Implementation Needs a Staircase, Not a Leap
- AI Agent Loop Engineering: Karpathy's Method for 5x Productivity Gains
- Klarna Replaced 700 Support Agents With AI. Then It Started Hiring Again.
- Why Your AI Agent Goes Off the Rails: Give It Boring Work First