Insights.

Essays behind the threads: stack, failures, Instance Knowledge, agent coordination, and lessons from building with five agents and one founder in the loop.

Field notes

Featured essays

How I run any AI voice tool through the same client delivery workflow

Voxyz AI

AI Team

Insights

Insights.

Field notes

How I run any AI voice tool through the same client delivery workflow

Install a skill once, use it everywhere

claude code-maxxing: treat claude code like a project loop

How to Use Claude Code to Learn Any Field: Turn Learning Into a Project That Runs

The more I use AI, the less I want to start from a prompt

I Tried a Ton of Claude Code Subagents. These 10 Are the Ones I Kept.

The Third Step in Building My AI Native Team: Teaching AI Employees to Speak Up

Turn the stuff you keep asking Claude Code/Codex to do into actual tools

Start with Repetitive, High-Judgment Work: Building Your First Skill Library

How to Build an AI Second Brain for Your OpenClaw/Hermes That Learns While You Sleep (full guide)

I Cloned Buffett and Graham with AI and Had Them Team Up to Automate My Investment Research

Dynamic Workflows: Claude Code Is Moving the Agent Plan from Chat into Executable Scripts

5 Lessons for an Agent Personality File: Get OpenClaw and Hermes Past the Generic Assistant

10 Lessons for Writing a Good AGENTS.md: Get Codex and Claude Code to Understand Your Project

From One AI Loop to an AI Team Workflow With Hermes and OpenClaw

How I run my AI team's simplest loop with OpenClaw and Hermes

20 Ways to Stop Wasting Tokens With Your OpenClaw / Hermes

Your OpenClaw / Hermes Gets Neurological Conditions Too: 6 Cases I've Diagnosed

12 Layers Every AI User Should Understand in 2026

A Framework for Agent Memory: Remember, Cite, Forget

Here's what an agent report people actually read looks like

I tried letting my scheduled agents deliver only HTML, and I'm not going back

An AI That Confidently Quotes the Wrong Note Is Scarier Than One That Admits It's Lost

Your Agent Needs a Wiki and a Recording, Not a Bigger Desk

The Second Step in Building My AI Native Team: Inbox First, Brain Second

The First Step in Building My AI Native Team: Shared Brain First, Boundaries Second

How to Quickly Recreate Any Website For Your Own Product

How to Set Up Your First 3 AI Employees in 30 Seconds

I built 27 OpenClaw agent packs from internet personality memes. My agent started talking different.

OpenClaw Best Practices After the Anthropic Split

I Stopped Collecting Agent Skills. Started Wiring Them Into Loops.

5 minutes to cross the skill gap between openclaw pros and beginners

I Read Through 1,902 Leaked Files From Claude Code. The Interesting Part Isn't the Code.

Claude Code Best Practices: From Tool to System

I Hardened My 5 AI Agents. They All Went Dark.

Everyone Says Quit Your Job and Go All In on AI. They're Wrong.

The more rules i wrote for my agents, the worse they performed.

Everyone teaches you how to install OpenClaw. Nobody tells you what happens after.

My Agent Finished the Job. The Money Hasn't Arrived.

I Built an AI Company with OpenClaw. Today, It Had Its First Reorg.

The Hidden Layer in OpenClaw Swarms: Make Them Disagree, See Who Survives

I Built an AI Company with OpenClaw. Now It's Hiring.

If I Were Starting AI Today, This Is Exactly What I'd Do

I Rent a Server for $8/Month to Run OpenClaw. 6 AI Employees Live Inside It. They Were Arguing at 3

I Turned My AI Agents Into RPG Characters. Now I Can't Stop Checking If They Leveled Up.

The Full Tutorial: 6 AI Agents That Run a Company — How I Built Them From Scratch

I Built an AI Company with OpenClaw + Vercel + Supabase - Two Weeks Later, They Run It Themselves