Snowbell AI assists customers in streamlining their LLM workflows, encompassing data preparation, prompt engineering, and evaluation & testing. With a comprehensive AI development toolkit, it makes building AI features more efficient and transparent.
At the beginning of 2023, my co-founder (an AI engineer) and I recognized a growing demand for a new approach to developing LLM-based applications. After conducting dozens of user interviews to gather and assess insights, we decided to build a platform that enables businesses to create LLM apps more efficiently and launch them with greater confidence.
As a co-founder, I wore multiple hats. My responsibilities included:
One of the biggest pain points for our target users is that developing with LLMs can feel like working in the dark. It's difficult to evaluate the performance of the features they've built using traditional tools. To address this, we developed a tool that allows users to run side-by-side tests and receive summarized results within minutes, all with just a few clicks.
Side by side experiment list - List view
Side by side experiment list - Visualization view
Create a new experiment
Conduct side-by-side comparisons of multiple prompts, parameters, models, and even model providers across a range of test cases.
Experiment detail page
Prompt playground
Prompt testing
Users have discovered that traditional 'unit test' tools are missing when doing prompt engineering. To address this, we created an inline testing feature that allows users to quickly test prompts on any query in the playground. It's fast and cost-effective.
Query set editor
Invite people to projects
