Skip to content

Smart home assistant demo

TypeSafe's official interactive smart-home demo of speculative fan-out: many questions in one call, code keeps the relevant answers.

Appproduction

This summary is based on how curated lists describe the project; its README was not available to review.

Overview

This is an official interactive demo in TypeSafe's documentation, set in a smart-home assistant. According to the directory summaries, it demonstrates the speculative fan-out pattern: asking many questions about one state in a single call, and letting code keep only the answers that turn out to be relevant.

The idea is that, because Jev answers questions in parallel over a shared state and charges for input once, it is cheaper and faster to ask every plausible question up front (for example which device, which action, which room) than to chain calls. No page content was fetched, so the specific questions and devices are not reproduced here.

What the decision model decides

TypeQuestionAnswers
ChoiceWhich device and action does this request target?(inferred)—
Yes / noSpeculative questions whose answers code may discard(inferred)—

How it works

  1. Take a user request in the smart-home demo
  2. Ask many speculative questions in one call
  3. Code keeps the relevant answers and acts

Strengths

  • Illustrates an official pattern for cutting round trips

Caveats

  • Grounded only in list summaries
  • Demo, not a product

At a glance

Type
App
Status
production
Runtime
Web demo

Use cases and integrations

How curated lists describe it

Frequently asked questions

What does the demo show?

Speculative fan-out: many questions in one call, with code keeping the relevant answers.

Why ask questions you might not need?

Jev answers them in parallel over one state, so one call can replace several sequential ones.

Where is it?

docs.typesafe.ai/demos/smart-home.

Related projects

  • Unofficial Jev operator lab: offline-first FastAPI app with primitives playground, cost lab, pattern pages and a TypeScript harness.

    Agent skillbetaPython
  • Agent skill for writing and improving programs that call Jev: question design, state structure, thresholds and diagnosing wrong answers.

    Agent skillproduction
  • Server behind api.typesafe.pro, a free anonymous System One-compatible endpoint that forwards to TypeSafe on the operator's key.

    Serviceproduction
  • Portable Agent Skill teaching coding agents to use Jev as a bounded judgment layer, plus an optional MCP bridge.

    MCP serverbetaTypeScript
  • Independent agent skill that makes a coding agent design, build, test and tune a bounded Jev decision layer with a contract first.

    Agent skillbeta
  • Agent skill that guides you in finding, designing and testing Jev decision loops, including when to keep logic in code.

    Agent skillbeta