Freeplay has been an essential tool in shaping our AI prompts. It’s made testing fast and intuitive, and helped us confidently set up evaluations to ensure quality and consistency. It has streamlined our workflow and let us iterate much faster, while building confidence across the organization. Lastly, the Freeplay team has been very supportive in helping us use best practices, and have been execuring quickly on product feedback.

We've been using Freeplay for a few months now and it has substantially cut down the time it takes us to ship and maintain AI features. It hooks seamlessly into our LLM-related code and allows us to quickly experiment on prompts, version control them, and create evals with gold standard datasets to ensure that our AI workflows continue to run reliably. The interface is intuitive and the SDK is shockingly easy to integrate while being flexible to our engineering patterns. They built the whole platform exactly like I would've if I built it myself - glad we found when we did!