Cookbooks & Demos

A 13-question regulatory briefing that shows batching every question into one call is 12.2x cheaper and 10x faster with no change in answers.

One question per query-candidate pair raises top-1 accuracy from 5% to 18% and top-10 accuracy from 38% to 62% on 40 CLERC legal queries.

Screen every message going into and out of an LLM app: a Noul describes possible hazards, a Score rates severity, and code thresholds the probabilities.

Classify documents through deep patent, retail product, biomedical, and source-code hierarchies using parallel beam search over Choice probabilities.

Classify SEC annual reports into 75 industry groups with one Choice each, then read confidence to decide when to fall back to a broader division.

A smart home assistant that uses TypeSafe to evaluate user requests, pick a tool, and fill its arguments from plain language.