New this week: OpenAI caching

This week, we rolled out support for OpenAI caching. When you make the exact same request with caching enabled, you'll get faster responses without paying for the additional call.

We hope you’ll try it out soon! Schedule a call to learn more.

Never built an AI feature? This week’s article is for you. We’ll walk through the evolution of building an AI-powered book recommendation app.

What we’ll cover in this article:

• Go beyond the standard chatbot interface

• When to use prompting, RAG, caching, and finetuning

• Iteratively test your AI product ideas

More from Velvet:

Read about why Find AI, an AI-powered B2B search app, uses Velvet to warehouse millions of LLM requests per week.

Read more →

We’re hiring a founding engineer! Seeking entrepreneurial full-stack engineers. Our system is built on Next.js, Typescript, Postgres, and OpenAI.

Learn more →