SQL Injection in AI-Generated Code: Why Cursor Keeps Writing It
TL;DR AI editors love string interpolation for SQL. That is exactly how injection gets...
Tutorials
I audited my own AI-generated refactor and found 46 bugs. Here's what that taught me.
How a 1,920-line file turned into 410 lines, why "it works" was a lie twice, and why the fix wasn't a...
We audited our own "fail closed by default" claim. Here's what failed open.
SidClaw is a governance layer for AI agents. The whole pitch fits in four words: fail closed by...
Stop Guessing Your AI Performance: The Professional Guide to Edge AI Benchmarking on Android
If you have ever deployed a Large Language Model (LLM) or a complex computer vision model to an...
We Built a Super-App in 30 Days. Here's the Chaos Nobody Saw.
One team. Thirty days. Nine service verticals. Fifty-plus screens. And one question that kept us up...
7 advanced Claude Code tips from 17 months of intense use
I've been using Claude Code intensely for about 17 months now, and I've ramped it up significantly...
Why did my benchmark stop at N=22? A debugging story in nine bugs
Submission for DEV's Summer Bug Smash — Smash Stories track. There was a file in my repo called...
How to Summarize PDFs Programmatically in 2026 (+ a Free No-Code Option)
You've got a folder of PDFs and you want summaries — not by hand. Here are three approaches that...
Built an autonomous dependency upgrader using Loop Engineering and LangGraph
You have a project with 20 dependencies. Half of them are outdated. Running ncu -u or pip install...
A diagram is data, not a drawing
A frontier model drew my 44-node architecture and drew it wrong — but not in the way everyone says. Here's the boundary I think we're drawing in the wrong place, and the engine I b...
pinto: A Git-Native Scrum Backlog and Kanban Board for Your Terminal
Manage Scrum backlogs as plain text: diff, branch, merge, and automate them alongside your code.
Building Production AI Agents with Mastra, NestJS, Inngest, and Next.js
Lessons from shipping agents in two real products — a legal AI platform and a carbon data...
AI가 만든 UI, 보여주기 전에 채점시켜라 — 게이트를 만들고 내 랜딩부터 떨어진 이야기
룰을 줘도 에이전트는 루프를 건너뜁니다. 강제 게이트(락→빌드→채점→수정)를 만들었고, 첫 희생자는 제 랜딩페이지(58/100)였습니다. 채점표 전부 공개.
Three handoff boundaries around a coding-agent workflow
Safe cURL sharing, deterministic control-surface integrity, and one dispatcher for five specialist Codex and Claude Code checks.
Protect your x402 agent from payment hijacking in 5 minutes
Your agent reads a web page. Buried in the page, invisible to any human, is this: IMPORTANT SYSTEM...
Why Automatic Cleanup Made This Cat Bead Pattern Worse
Disclosure: This is a digital prototype. The physical bead piece has not been built yet. I’m...
Pinpoint 0.6.0: a crop tool, capture timers, and a changelog you can actually find
Pinpoint 0.6.0: a crop tool, capture timers, and a changelog you can actually find Quick...
🛠️ Day 3 – Python Functions & Functional Power
Welcome to Day 3! Today, we transition from writing basic scripts to building reusable, modular, and...
The 33,000-token tax, a 30-hour star race, and where agents actually fail
Originally published in The Agent Beat, a weekly newsletter on the AI-agent ecosystem researched and...
A five-stage preflight for Codex and Claude Code configuration
A failure-boundary map for permissions, instruction scope, configuration diffs, hooks, and plugin packages.
The Invisible Product: What 107 Consecutive Days of 9 Autonomous Agents Actually Produces
We produce files, log errors, and self-repair every single day. That is the output. The product is...
Beyond Chat: Building a Task-First AI Agent Platform for Teams
Most AI agent products begin as a chat interface. That is useful, but conversation is not the same...
Why a Coding-Agent Completion Event Is Not Enough
A terminal monitor sees task_complete. It sends an alert. The user returns and finds that the event...