Intent routing
Classify what the user wants and send the request down the right branch.
39 rows are filed under this pattern, 37 of them with code. Rows are listed as the catalogue orders them: official first, then rows with code, then by stars.
Filter and search them in the catalogue →
Rows marked “not Jev itself” or “shadow mode” stay listed, but they are not examples of deciding with Jev.
-
Demo: Smart home assistant
Runnable demo code for a smart home assistant that evaluates user requests with typed decisions.
-
Pattern: Confidence-gated routing
Treat confidence as a second axis: the answer tells you what, the confidence tells you whether to act on it.
-
Pattern: Intent routing
Classify an incoming request and route it to the cheapest adequate handler: deterministic code, a specialist LLM, or a person.
-
AutoGPT TypeSafe blocks
Seven production blocks — choice, score, yes/no, ask-many, route, pick-best, filter — with a UTF-8 byte budget, verbatim wire capture and eleven test files.
-
Airflow LLMBranchOperator with Jev
Turns downstream task ids into a choice option set, with a minimum-confidence gate that routes uncertain runs to a human.
-
Inbox Zero: seven email decisions
Seven distinct email decisions, each with its own separately chosen threshold, falling back to the normal LLM on any error.
-
jev-chat-jarvis
An Android reply co-pilot that judges intent, timing and risk from on-screen text, while separate models handle OCR and drafting.
-
Real Python: hello-jev
A teaching example with a deliberate control group: the same station-enquiry task written in plain Python that only accepts Y/N, next to a Noul that reads intent.
-
ai-cookbook: Jev track
A graded course from a first call through each primitive, state shapes and criteria, to ticket triage and a multi-step workflow, mirroring all four official patterns.
-
shapeshift
One text box that turns into the right card as you type (event, checklist, timer, bill split and more). With a TypeSafe key one Jev call answers 14 questions: which card, plus choices, nouls and scores such as urgency or video call; code parses dates and amounts. Offline, keyword rules answer.written by a model
-
foreman
A software-factory foreman that uses Jev to decide what an agent pipeline should do next.
-
mu
Coding agent and desktop app built on pi that asks Jev at 38 decision points which tool-output chunks enter the context, which stale tool results to drop, whether a rule-flagged command was asked for and whether fetched pages or MCP output carry injected instructions.
-
jev-search
Jev-driven web search: chooses the recency window and the best query rewrite, then reranks results in batches with one noul each.
-
狗头军师 Jev Chat
Chat-reply assistant (desktop overlay, Android floating assistant, iOS keyboard) built on Jev Android. From the visible chat or a screenshot it asks Jev the literal question, the other person's intent, a danger level, whether to reply now and the best action, then has Jev pick among drafted replies.written by a model
-
jev-voice-browser
Voice-driven browser control where target criteria are rebuilt per request from the live element list, always including a none option.
-
hyperedit
An AI video editor routing an editing instruction to an operation, a target clip and a track, with a keyword router as fallback.
-
taskuary
Local-first work assistant that turns mail, chats and tickets into tasks your coding agents do, sending nothing until you approve. With a TypeSafe key, Jev triages: nouls asked as the owner would judge, with their profile and past verdicts in the state, such as whether to make an item a task.written by a model
-
jev-chat: a tool-calling chatbot with no LLM
A chat bot that does tool calling with no language model anywhere: one request asks the request kind, the tool, and every tool's arguments at once.
-
ha-jev
A Home Assistant integration: typed answers about the house as sensors, noul, choice and score actions for automations, and a conversation agent.
-
hono-jev-router
Routes HTTP requests by meaning — a semantic router for a web framework.
-
jev-mail-classifier
Classify your inbox with Jev (TypeSafe's System One model) — tag, move, flag, and notify, all config-driven.upstream description
-
jevyoumean
Semantic "Did you mean?" for any CLI — wraps commands and uses TypeSafe's Jev to match subcommand typos by intent, not edit distance.upstream description
-
jev-ai-sdk-form-router
Route form submissions to the right people with Jev and AI SDK.upstream description
-
jevcache
Skip expensive LLM calls when TypeSafe Jev says same intent. OpenAI-compatible local cache proxy — npx @kushalicious/jevcache
-
typesafe-jev-workflow
A small async LangGraph workflow: each mocked email goes to Jev as a typed Choice (invoice or general) and the graph routes it to a demo handler. Classification makes real API calls; the handlers only set a destination.
-
jev-phishing-bench
Jev (TypeSafe) vs Claude Haiku 4.5 on 2 000 phishing emails: accuracy, calibration, latency, cost. Reproducible benchmark.earlier upstream description
-
JevT++
C++20 library that turns runtime text, JSON or objects into enums, booleans and scores through compile-time schemas, with full distributions and explicit abstention. Runs local Laya models in-process (ONNX Runtime or ggml) or Jev through an opt-in remote backend; latency metrics and a Mario demo.written by a model
-
jev-inbox-queue
Turn an inbox into a short action queue with Jev (TypeSafe System One)upstream description
-
A deep dive into Jev, TypeSafe's System One model
The densest independent explainer: code in JS, Python and the AI SDK, all three answer shapes, the advanced patterns, and an honest list of where the model fails.
-
Example: confidence-gated escalation
Routing with an act-or-escalate gate, where the policy function is deliberately left unimplemented because the thresholds are yours to choose.
-
Jev AI Use Cases
Walks through use case after use case — agent routing, an in-agent decision layer, ticket triage — each with a concrete option set and a sample response.
-
Jev on Netlify AI Gateway
Zero-config access from a Netlify function: use the official SDK with no API key, base URL or provider setup, billed through Netlify credits.
-
jev-eval
A third-party check of Jev against two LLMs under identical conditions: routing booking inquiries to a photo-shoot service for tourists in Japan, sixty synthetic messages in four languages.
-
lanebreak
LaneBreak — support ticket priority+routing via TypeSafe Jevupstream description
-
langchain-typesafe
The LangChain integration: a classifier plus experimental middleware for model routing and for gating risky tool calls before they run.
-
Using TypeSafe Jev with the AI SDK
The richest Vercel walkthrough: single and multi-question calls, probability-threshold routing, and unit tests with a mock evaluation model.
-
Jev router: how model routing works, and 16 routers compared
Explains a router that asks Jev which model, tool or skill the next turn needs before anything is spent, why routing down and back up can cost more than not routing, and compares 16 routers for Claude Code, Codex and OpenRouter.
-
jevai.org community showcase cases
Nine worked community scenarios: intent routing, invoice classification, news filtering, product tagging, moderation, claim verification, CSV validation and more.