TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Writing an LLM Eval with Vercel's AI SDK and Vitest

1 pointsby gulcin_xataabout 1 month ago

1 comment

gulcin_xataabout 1 month ago
Recently we launched Xata Agent, an open-source AI agent which helps diagnose issues and suggest optimizations for PostgreSQL databases.<p>To make sure that Xata Agent still works well after modifying a prompt or switching LLM models we decided to test it with an Eval. In this blog, we&#x27;ll explain how we used Vercel&#x27;s AI SDK and Vitest to build an Eval in TypeScript.