FAQ

Short answers to the questions we get asked most often.

01
Does Prompt Assay support regression testing on prompt changes?
Yes. Regression testing reuses your existing eval suite to score version N vs N+1 of a prompt side-by-side, with manual or auto-on-version triggers.
02
Which LLM model should I pick?
Decision matrix: speed vs quality vs cost for each supported model.
03
Can I use a local or self-hosted model?
Today: Anthropic, OpenAI, Google only. What's on the roadmap.
04
How much does a single call cost?
Typical cost ranges for the most common models and an example calculation.