Skip to content
JevDirectory.org
PatternsTool calling

Function calling

Turn natural language into typed function calls: closed-set arguments become Choice questions and optional ones become Nouls.

Open docs.typesafe.aiAll 117 terms
Category
Patterns
Also known as
Tool calling
Related terms
4
Directory entries
11
Docs
docs.typesafe.ai
Added
2026-09-24

Definition

The cookbook maps 10 trading functions with 28 fillable closed-set arguments into 54 questions per command, sent in one request. A stated Noul marks an argument optional, so a no leaves the function's default in place; the sample command mapped at 0.82 confidence with the benchmark argument weakest at 0.78.

Free text, numbers, and dates never get a question and keep the function default, so those arguments still need your own parsers. The smart-home demo applies the same shape to home automation requests.

Tagspatternstool-callingagents

Related terms

Definitions that connect to this one.

ChoicePick one option from a set you define; returns the selected option, a probability for every option, and confidence.PrimitivesNoulThe yes/no primitive: one probability from 0 to 1, where the value is the answer and no separate confidence is returned.PrimitivesIntent routingClassify intent with a Choice and complexity with a Score, then send each branch to deterministic code, a specialist model, or a person.PatternsPre-parsed value extractionRegex finds candidate spans, then Jev picks the requested one so code copies a verbatim value that cannot be invented.Patterns

From the directory

Cookbook: Function Calling
Turn natural language into typed function calls: closed-set arguments become Choice questions, optional ones become Noul questions, and 54 questions ship in one request for a trading assistant.
Cookbooks & DemosDocs#official#cookbook#tool-calling
Official
Demo: Smart Home Assistant
A smart home assistant that uses TypeSafe to evaluate user requests, pick a tool, and fill its arguments from plain language.
Cookbooks & DemosDocs#official#demo#tool-calling
Official
TypeSafe AI Rust SDK (community)
0GitHub stars
A community Rust port of the official Python SDK with the same primitives, wire format, retries, and error semantics, plus derive macros for typed questions and answers.
Repos & SDKs#community#rust#sdk
Communitycommunity-ports/typesafeai-sdk-rust-communityRust
jev-eval-agent
105GitHub stars
A personal-assistant agent with 100 mocked tools that measures how many steps a task takes when the LLM picks the tool versus when Jev picks it before every model step.
Practices & Patterns#community#typescript#agents
Communityvinilana/jev-eval-agentHTML
pi-typesafe-jev
3GitHub stars
A pi extension that exposes TypeSafe Jev judgments as five tools, calling POST /v1/systemone directly with native fetch so your code and users keep control of thresholds, weights, and actions.
Tools & Integrations#community#typescript#agents
Communitylegacybridge-tech/pi-typesafe-jevTypeScript
pi-typesafe
45GitHub stars
A Pi extension and library that gives the agent and other extensions one consented, key-managed Jev client, with a batched typesafe_evaluate tool for classify, triage, compare, and score judgments.
Repos & SDKs#community#typescript#sdk
CommunityDevMortimer/pi-typesafeTypeScript

5 more matching entries in the full directory.

From the community

Posts from builders shipping with Jev right now.

Follow @typesafeai

A Krunker-inspired FPS, decided by Jev

Neel Patel
Neel Patel
@Neel490
·

Maybe I’m just washed, but Jev is beating me at my own game. Built a Krunker-inspired FPS where you 1v1 Jev. Try it out yourself: jev-arcade.vercel.app/duel

Watch on X
Diogo Almeida
Diogo Almeida
TypeSafe AI
@CompleteSkeptic

After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x

Watch on X
Reply
Read more on X

Pixel art out of 256 multiple-choice questions

Aryan Singh
Aryan Singh
@just_aryansingh
·

I turned @typesafeai Jev model into a pixel art model. 256 multiple choice questions, one per pixel, plus refinement passes. These were the best results out of the bunch I tested. Code: github.com/Wizhill05/type…

Image
Image
Image
Image
Diogo Almeida
Diogo Almeida
TypeSafe AI
@CompleteSkeptic

After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x

Watch on X
Reply
Read 1 reply

An Elixir port of the official SDK

jod: Zod validates data, Jev judges it

Loki: a self-improving harness with a Jev companion

Jev as an LLM guardrail inside Agentgateway