Build better LLM-powered products, faster.
Today’s workflows for iterating LLM-powered software are slow and janky. So Forestwalk is researching better ones. For example:
ScoutEvals
Runs evals and grading for LLM-powered products. If evals, testing, and prompt iteration are important to your team, let's talk.
We’re learning from the best AI engineering teams, finding gaps, sharing what we learn, and building product experiments.
We’re just getting started. There sure is a lot to do.