Welcome to Ted’s Content Factory#

Everything published here—books, apps, and everything else—is content. I’ll keep adding new kinds of content over time.

About#

• I’m a software engineer currently building AI-powered applications, and I also run this “factory.”
• Profile: iamted.kim

Content#

• Books: Serialized and organized “books.” (Go to Books)
• Apps: Notes on apps I’ve personally built, launched, and operated. (Go to Apps)
• Widgets: Experimental tools / mini games built with just HTML and JavaScript. (Go to Widgets)
• Notes: General posts that don’t fit under Books/Apps (tech, life, opinions). (Go to Notes)
• News: Short curated briefings on AI and technology updates worth checking. (Go to News)

Latest Content

I Decided to Call Them Harness Skills — Breaking the Illusion of Doing Well and Opening Up My Harness

A story that began with a question: what should we call tools like LLM Wiki and GStack? With no standard term available, I named them 'harness skills,' reflected on how confidence in my own harness became a trap for growth, and then surveyed the most widely loved harness skills.

An Agent That Keeps Working After the Laptop Closes: Remote Development with Lightsail, Hermes, and Discord

A practical record of moving an AI agent from a local laptop to an always-on remote environment with AWS Lightsail, Hermes Agent, Discord, and a Docker sandbox. It covers the architecture, security posture, and setup process for continuing development work from mobile.

How Product Development Processes Should Change in the Age of AI Agents

An essay on how product teams should handle code changes created directly by planners using AI agents, with a focus on intent transfer, review, and harnesses.

Math Track

A single-player mental-math trainer: roll a die, move around a square track, and keep a running total of the operations at each cell. Enter the correct final value when your pawn returns to the start to advance to the next level.

How to Add Coding Runtimes to an AI Agent Web Service

This essay explores how an AI agent web service can adopt coding runtimes such as Claude Code, Codex, and Gemini CLI, which tools are worth evaluating first, and where the real product moat likely lives.

Hermes Agent — Is It the Luxury Brand of AI Agents? A First Impression

A record of getting to know Nous Research's Hermes Agent. From analyzing a teammate's Pulumi deployment, to installing it locally on a Mac and connecting it to Slack, to a first impression and the operational questions worth following up on.

Claude Managed Agents — Can It Replace Your Existing Agent System?

A practical comparison of Anthropic's Managed Agents with existing multi-agent systems, covering architecture design, Memory Store, and governance considerations for real-world adoption.

In the AI Era, How Will Work Be Divided Again?

An essay on how AI and internal harness environments are changing the way work is divided inside companies, and why ownership and quality systems matter more than rigid job titles.

Where Should You Use Codex? A Guide to CLI, App, Cursor, and Claude Code

A beginner-friendly guide to the different environments for using OpenAI Codex, what stays the same across them, what differs, and when each option makes the most sense.

Latest News