Instrument your LLM calls to analyze AI costs and usage
SMRTR summary
Tinybird has added AI capabilities to create data projects, write tests, and generate mock data using prompts. They implement these features with Python and TypeScript backends, utilizing Vertex AI and libraries like LiteLLM and Vercel AI SDK. The company monitors various metrics for their AI features, including costs, performance, and user adoption. They've developed a real-time monitoring web app and plan to release an open-source template for AI application instrumentation.
SMRTR provides this summary for quick context. The original article belongs to Daily.dev.
Read the original article