Introduction & quick start ↗
Start here to understand state, questions and answers before sending a request.
docs.typesafe.ai
A guided path through TypeSafe’s documentation, demonstrations and published evaluations.
Start with the basics, choose a workflow, then check limitations and evaluation examples.
Start here to understand state, questions and answers before sending a request.
docs.typesafe.ai
Choose a category, an ordered rating or a yes/no probability to match the result your code needs.
docs.typesafe.ai
Use a decision and its confidence to choose when to act and when to ask for review.
docs.typesafe.ai
Ask candidate questions together, then let code use the relevant answers. Useful when calls do not truly depend on one another.
docs.typesafe.ai
An example of device-control questions, result selection and a fallback to a text-generating model.
docs.typesafe.ai
Distinguish confidence from answer probability. Noul has no separate confidence field.
docs.typesafe.ai
Read the documented weak spots and turn relevant ones into test cases for your application.
docs.typesafe.ai
Check model identifiers, pricing and input limits before configuring a deployment.
docs.typesafe.ai
Find the side-by-side, Doom and Wikiracing demonstrations. Read the conditions beside each demo.
typesafe.ai
Explore four publisher-evaluated workflows. Their reference answers are based on model consensus.
evals.typesafe.ai
Inspect a customer-service workflow, including inputs, code policies and prediction disagreements.
evals.typesafe.ai