I deleted every fitness app I tried. So I built my own — in 17 days, after work.
I'm a back-end developer in Korea. Nine years of Java, Kotlin, and Spring — all of it...
Tutorials
"My First Terraform Workflow on Azure:
A hands-on walkthrough of provisioning and tearing down my first Azure resource using Terraform as...
Whisper-powered transcription, explained: what actually happens to your audio
If you have used any AI transcription tool in the last two years, there is a good chance a...
Your Background Subagents Can Leak Secrets — Build the Isolation Model
Developers flagged a freshly filed, reproducible issue that should make anyone running background...
737x faster LangGraph checkpoints, and the case where Rust lost
Run a LangGraph agent long enough and the model call stops being your bottleneck. The plumbing takes...
The AI orientation tax: it's missing context, not discipline
You have eleven things in flight. Three of them are "almost done." You can't remember which three....
Writing Evals for an LLM Security Tool: How I Know It Didn't Get Worse
Every time a new model ships, I face the same question for spectr-ai: does my contract auditor get...
Building LaunchPad: one product brief, 42 launch channels, and the bugs that almost sank it
Launching a Product: A Translation Problem Launching a product is a translation problem....
Stop Letting Code Reviews Become Your Teams Bottleneck
Stop Letting Code Reviews Become Your Team's Bottleneck Your team's code review process is...
Your New Prompt 'Feels' Better. That's Not an Eval.
You tweak the prompt. Run it against the three examples you always use to sanity-check. It looks...
🚦 I Built an AI-Powered Traffic Intelligence Platform That Predicts Congestion Before It Happens
Traffic congestion isn't just frustrating—it wastes fuel, increases pollution, delays emergency...
What If the Model Knows It's Being Tested?
Inside the Black Box — Post 2 of 6 Series: Inside the Black Box — A developer's honest...
Cosine similarity finds the topic, not the buyer
Cosine similarity finds the topic, not the buyer I build a small tool called Leadgram that...
Most Evals Measure the Wrong Thing
Reading through the awesome-evals list on GitHub yesterday, I realized something I've been circling...
How I Run Multiple Claude Code Agents in Parallel Without Collisions
TL;DR I started running multiple autonomous Claude Code sessions on the same repo at once...
I Built an AI Agent With Tools. The First 50 Calls Were a Disaster.
The Demo That Almost Lost Me the Project I spent two weeks building the agent. It could...
Use Xcode MCP Instead of xcodebuild to Save Disk Space and Time in Agentic iOS Development
TL;DR - When setting up an AI agent for iOS development, the default approach is to have the agent...
The Old Way of Publishing MCP Servers Is Gone. Here's What Replaced It.
I Assumed It Would Be Easy I've been building MCP servers for a while now. Filesystem...
The Notification That Lied to Me
I was three projects deep. Project A had a review open in one VS Code window. Project B was running...
Make your Web site natively readable by AI Agents (SearchGPT) in 1 line of code
The web is changing. Users are no longer just Googling your website—they are asking ChatGPT,...
How I run a business on AI agents: the exact setup
NexBDM (my South African AI automation company) runs on AI agents every day: the inbox, the marketing...
#11 When AI Coding Tools Were Dumb (and Nights Were Fun)
I had decided to move everything onto our own server. The hospital ran a small NAS — a box on the...
I built an AI agent that runs a local business's weekly marketing (Next.js + Gemini)
For the last couple of weeks I've been building Bloom, an AI marketing agent for local businesses...
Testes de arquitetura como guardrail pra IA
Eu construo SaaS sozinho e programo com IA o dia inteiro, ela é rápida, entrega feature, resolve bug...