testy.coolTools & Tech
Flex Inference: 50% Off LLM Calls on Gemini, OpenAI, and Bedrock
Every major AI provider now offers half-price inference if you can tolerate a few extra seconds of latency. One parameter change. Same API. Here's how it works and why.
Blog
Latest Posts
Newest first.
Lab Notes
A Better Way to Clone Screenshots to HTML
Using Gemini's bounding box detection to get precise measurements when converting a screenshot to code. Plus how prompt caching and flex inference make the multi-pass approach surprisingly cheap.
Tools & Tech
UCP - How to Actually Make Money With It
Universal Commerce Protocol lets AI agents buy things. Here's how developers can monetize it and what store owners need to know.
Tutorials
Setting Up SSH for Claude Code
How to configure SSH so Claude Code can run commands on remote servers
Start Here
Browse
By category.
Tools
A Few Tools
Things I built and use.
Tool
Video Breakdown
Paste a YouTube URL. AI watches the video and writes a scroll-synced text breakdown.
Tool
LLM Price Calculator
Calculator for checking API costs across Claude, GPT, and Gemini, including prompt caching.
Tutorial
CSS Clamp Calculator
Clamp() calculator plus the tutorial explaining the math behind it.