Codevolution takes a customer message from the TypeSafe playground into TypeScript, explaining Noul, Choice, and Score responses before combining them in one request. The closing examples make the boundary clear: use Jev for bounded judgments, a text model for writing, and ordinary code for exact calculations.
Original by CodevolutionGetting startedBeginner22 min 12 secPublished
Use Noul for a yes-or-no probability, Choice for supplied categories, and Score for an ordered scale whose levels have explicit descriptions.
Batch independent questions over the same state; one question does not get to read another question’s answer.
Keep writing and summarization with a generative model, and use deterministic code for arithmetic, item counts, and date comparisons.
Worth knowing
The customer-message examples illustrate the API rather than measuring classification accuracy; vendor speed and pricing comparisons are not independently tested.