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.

Show HN: CLI for testing and evaluating LLM prompts and outputs

2 pointsby typpoalmost 2 years ago
Hi HN,<p>This project has grown a lot recently and figure it&#x27;s worth another submission. I use this tool for several LLM-based use cases that have over 100k DAU. It works pretty simply:<p>1) Create a list of test cases<p>2) Set up assertions for metrics&#x2F;guardrails you care about, such as outputting only JSON or not saying &quot;As an AI language model&quot;<p>3) Run tests as you make changes. Integrate with CI if desired.<p>This makes LLM model and prompt selection easier because it reduces the process to something we&#x27;re all familiar with: developing against test cases. You can iterate with confidence and avoid regressions.<p>There are a bunch of startups popping up in this space, but I think it&#x27;s important to have something that is local (private), on the command line (easy to use in the development loop), and open-source.

no comments

no comments