from Hacker News

Hey HN! I built Experiment to solve a common frustration in LLM development: the lack of proper tools for prompt engineering experimentation. Here's what makes it different:

Key Features:

- Load and edit chat completion logs from CSV files

- Fork and modify specific conversation entries

- Run inference via Anthropic, Mistral, and OpenAI

- Define custom tools using JSONSchema format

- Visual tool usage analysis with collapsible, sorted key-value pairs

- Full mobile support and available as installable PWA

Technical Highlights:

- Built with React using custom isomorphic architecture

- Implements streaming SSR and static HTML generation

- Runs on GitHub Pages or as a native binary (Mac/Linux/Windows)

- Progressive enhancement for optimal performance

Why I Built This:

Working with LLMs, I found existing solutions were either too basic (editing code directly) or too rigid (chat UIs with fixed tools). Experiment bridges this gap, offering a flexible middle ground for developers.

Try it out: https://actualwitch.github.io/experiment GitHub: https://github.com/actualwitch/experiment

Would love to hear your thoughts, especially on the architecture choices and developer experience!