AI Tutorials & Practice

Two months ago I gave an agent a simple job: log into a vendor portal, download last month's invoice...

In 1997 a Pokémon episode aired in Japan with a four-second red-and-blue strobe. 685 children went to...

We've all been there. A teammate walks over (or pings you on Slack) with a massive chunk of...

While Git Flow (specifically the AVH edition) remains a solid branching model for managing releases...

An MCP server can expose the perfect tool and the model can simply not call it. Nothing is wrong,...

Title: A reader calibrated the guard's threshold. The next reader found the heartbeat's blind...

0. Introduction Long before the emergence of autonomous machines, humanity began imagining...

Macula is a mesh network for services and applications, built on Erlang/OTP: a node dials out over...

I built Pixel Patrol for the All Things Agentic hackathon, and this post is part of that submission....

For over a decade, we religiously used the well architected framework (WAF) in design reviews....

If you use Cursor, Claude Code, or Windsurf daily, you’ve probably hit this wall: You spend 45...

One repo, one PC, several agents working at once - and the merge step is just git.

Four spec-driven development standards rewritten on the same baseline, and why two side projects ended up on two different ones.

Why software decoupling is really about the physics of data, independent memory pointers, and stop-and-start boundaries—and how turning your codebase into a 2ms SQLite AST changes the game for humans and AI agents.

When you build a security app as a solo developer, the hardest engineering problem isn't writing the...

A follow-up: the 'fushi' catalog tool's public page finally reads live updates from the owner's editing tool, with a draft/publish flag and cross-tab sync.

Offload cross-origin preflight handling and header injection to Google Cloud Load Balancing with native CORS support on GKE Gateway.

After sixty-seven published posts here, the comments have become one of the best parts of the work....

I built an agent that coordinates eldercare for my mother in India, and the interesting part was not...

Latest release: v0.2.2 — Aug 29, 2026 I did something I usually try hard not to do in a field...

Last week I wrote about the French voiceover API that only accepts payment from robots. Today: the...

I built a code factory where a manager agent delegates a real backlog to engineers in isolated workspaces. Three things about it were wrong, and only the log said so.

I built CrisisMesh for the All Things Agentic Hackathon, and I created this post for the purposes of...

Tres capas de contexto para un agente de código, ordenadas por garantía Una migración tiró...

Why autonomous LLM agents hallucinate in production and how to implement retrieval-augmented orchestration to enforce human-in-the-loop correctness.

Hello, I'm Maneshwar, and I'm building LiveReview — a blast-radius aware AI code review built for...

AI agents can already browse a site, find a form, type into it, and click Submit. That works—until...

Maintaining an open-source project is a demanding journey that requires significant focus. The Claude...

I started building The Verifier because of a slightly uncomfortable thought: What if an AI gives...

In the last part, we worked up from the foundational problem to the key components of a RAG system....

Most MCP security writeups (including a few of mine) focus on a single server: does this one tool...

Last week I needed to give my AI agent a memory that connects facts instead of just listing them. Not...

Building AutoFix-Agent: How I Taught an AI to Fix Broken CI/CD Pipelines in 38...

The tests, in principle. But the agent wrote those too, out of the same understanding of the task, so...

Chapter 1 — Core Foundation 1.1 Objective The first version of ACAI should...

Intro I recently read an article about a VC who uses AI to boost his productivity. He...

The assumption every RAG demo makes Standard RAG assumes the user's question maps onto one...

In Part 1, I laid out three options for where to draw the isolation boundary around an AI coding...

TL;DR I had a feature branch that drifted five months behind main, and rebasing it...

Part III — Teams of Agents, a Post-Mortem, and the Frontier Part I defined eight failure...