Jev for Home Assistant
Turn Jev answers about household state into Home Assistant sensors and automation responses.
A focused collection of projects and source materials.
Public projects, checked against their original sources.
Turn Jev answers about household state into Home Assistant sensors and automation responses.
Use Jev through the AI SDK evaluation API, with Choice, Score, and Boolean questions in one request.
Explore a Neo4j graph by asking Jev which relationship to follow and whether the goal is reached.
A RubyLLM 2 provider that expresses Jev questions through RubyLLM's structured output interface.
A community n8n node for adding typed Jev questions to automation workflows.
An agent-loop experiment where Jev chooses actions and a LangChain model supplies text.
Small Pydantic AI examples that use Jev at prompt, tool, and application decision points.
Inspect typed quality signals while drafting an X post.
Replace flagged Spanish words with beeps using timestamped transcripts.
Explore Jev workflows for tickets, operational alerts, and deployment risk.
Use Jev for automatic model selection and typed evaluations in agents.
Send typed evaluation questions from shell scripts through AI Gateway.
Add a Jev decision companion to the Loki agent.
Display typed Jev answers and probability cards inside Agent Zero.
Route example email intents through an async LangGraph workflow.
Place Jev judgments in an HTTP inspection and forwarding service.
Integrate typed Jev requests into Laravel services and tests.
Ask Choice, Noul, and Score questions from PostgreSQL.
Add Jev configuration, usage records, and confidence policies to Rails.
Interpret Home Assistant voice commands with batched Jev questions.
Prototype Jev semantic checks for a Mellea generation loop.
Browse reusable React components for TypeSafe-style decision interfaces.
Turn a natural-language request into choices from a fixed UI catalog.
Read writing diagnostics through a playful compiler-style interface.
Evaluate a paper’s presentation, clarity, and completeness.
Apply your own typed questions to selected CSV rows.
Inspect separate Jev checks for clarity, filler, tone, and actionability.
Bring a CSV and inspect Jev classifications in a distribution chart.
An official walkthrough of batching home-control questions and using only the relevant answers.
Start with the playground, make an HTTP request, and translate a first evaluation into Python.
Understand the three question types, the answers they return, and when to use each.
Explore fan-out, confidence-based routing, composite scoring, and intent routing.
The request and response contract for calling Jev directly over HTTP.
TypeSafe's model-specific notes on failure modes and how to structure questions around them.
TypeSafe's published comparison of structured workflows and single-prompt approaches.
Try another keyword or clear your filters.