OfficialCookbooks & Demos

Cookbook: Guardrails for LLMs

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.

Open docs.typesafe.ai

Category: Cookbooks & Demos
Published by: TypeSafe AI
Author: —
Added: 2026-09-15

Tagsofficialcookbookguardrailsmoderation

More like this

Cookbook: Parallel Questions

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.

Cookbooks & Demos#official#cookbook#batching

Official

Cookbook: Re-ranking

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.

Cookbooks & Demos#official#cookbook#reranking

Official

Cookbook: Hierarchical Classification

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

Cookbooks & Demos#official#cookbook#classification

Official

Back to all resources