Single-call decision models are cheaper and faster than LLM structured outputForcing a model's response to match a schema, so downstream code can parse it instead of guessing at prose.Full definition → for routing and classification. This index measures their calibrationHow well a model's confidence matches reality — a calibrated model saying "90% sure" is right about 90% of the time.Full definition → and when they should abstain.
Terms in this piece · Glossary
hallucination — When a model states something false with full confidence — inventing facts, citations, or APIs that don't exist.
tool use — A model's ability to call external functions — run code, search the web, edit files — instead of only generating text.
structured output — Forcing a model's response to match a schema, so downstream code can parse it instead of guessing at prose.
calibration — How well a model's confidence matches reality — a calibrated model saying "90% sure" is right about 90% of the time.
