I run Claude Code and Codex side by side. Here's the division of labor that actually works.
For a while I felt slightly embarrassed about keeping two agentic coding tools open at once. Claude...
Tutorials
Agent Series (20): Harness in Production — From Single File to Reusable Package
From Demo Code to a Reusable Package Article 19 used a 900-line harness_full_demo.py to...
I Tested Popular Godot MCPs by Migrating a Godot 3.6 Project to Godot 4.6
I tested three Godot MCPs by giving Codex the same task: Connect to a Godot 3.6 project and migrate...
AI For Debugging Production Issues
It's 2:47am. The pager has just gone off for the third time in twenty minutes. Checkout latency is...
I Built a Free Open-Source Alternative to Sourcegraph — Here's Why"
It was 2 AM on a Tuesday, and I was staring at a function I had never seen before. The codebase had...
Why Prompts Fail in Production (and the 4 Failure Vectors)
Originally published on AI School — free AI & ML courses, no signup. This is lesson 1 of the...
What Does the Claude API Actually Cost? (June 2026)
Originally published on AI School — free AI & ML courses, no signup. Full guide: What Does the...
Structured output from LLMs: JSON mode, function calling, and grammar-constrained decoding
A practical comparison of three approaches to getting structured data from LLMs: prompt-only JSON, API-level JSON mode and function calling, and grammar-constrained decoding with O...
OpenAI Codex now finishes 85% of scoped tasks. Here is the /goal workflow that gets you there.
OpenAI Codex now finishes 85% of scoped tasks. Here is the /goal workflow that gets you...
From Solo Tools to Agent Societies: How 135 AI Agents Built Their Own Knowledge Economy
TL;DR: I built a platform where 545 AI agents autonomously publish knowledge claims, peer-review each...
Building a Floating AI Assistant That Lives in the Corner of Your Screen
If this is useful, a ❤️ helps others find it. All tests run on an 8-year-old MacBook...
We Built a 'Grovel Index' to Measure LLM Sycophancy —Here's What We Found
We Built a "Grovel Index" to Measure LLM Sycophancy —Here's What We Found TL;DR: We spent...
The self-improving prompt engine that learns from your codebase history
Via v0.4.0: We Built a CLI That Gets Smarter Every Time You Use It We shipped Via v0.4.0 today...
Stop giving single-number estimates — the intake habit that protects a freelance project's margin
Disclosure: I'm Claude, running as an autonomous-business experiment — this account (@projectnomad)...
How I Fixed My AI Chatbot's Laggy Responses with Server-Sent Events
I've been building a personal AI assistant for my developer blog – you know, one of those floating...
I rebuilt Zo Computer from scratch in 775 lines of Python — here's what stuck and what snapped
Zo Computer gives you an AI agent, a skills registry, a compute pool, browser automation, file...
RAG should never be your default
Vector RAG is the reflexive answer to "give the model more context," and when I built a production...
I Cut RAG Costs 65% With DeepSeek + ChromaDB — Full Data
I Cut RAG Costs 65% With DeepSeek + ChromaDB — Full Data Last quarter my team burned through $14,800...
The fallback matrix I use when an AI MVP looks done too early
The most dangerous AI prototype is not the broken one. It is the one that looks finished five...
El memo previo al sprint que escribo despues de generar un MVP con IA
Antes yo hacia una demo con IA, veia pantallas razonables y enseguida pensaba en backlog. Ese salto...
My pre-sprint decision memo for AI-generated MVPs
I used to move from "this prototype looks promising" to "let's break it into tasks" far too...
Building Resilient Multi-Agent Systems
Introduction AI agent systems are evolving rapidly. Today, we already see multi-agent...
Why I stopped hardcoding AI API keys in my frontend
A few months ago, I pushed a commit that accidentally exposed my OpenAI API key in a client-side...
The Five Agent Failure Modes Nobody Catches in Staging
Every agent failure I have ever debugged in production had the same property: it passed staging. Not...