testy.coolTools & Tech
Tooling notes, implementation details, and small experiments.
LLMsinferencecost-optimizationGeminiOpenAIAWStool
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.
testy.cool•May 12, 2026•4 min read
agentscommerceprotocolsaistandards
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.
testy.cool•January 23, 2026•4 min read
