---
type: "raw_signal"
id: "llm-typesafe-0-1a0-66b65b"
slug: "llm-typesafe-0-1a0-66b65b"
title: "Simon Willison released llm-typesafe 0.1a0, an LLM CLI plugin that adds support for TypeSafe AI’s Jev model"
description: "Simon Willison released llm-typesafe 0.1a0, an LLM CLI plugin that adds support for TypeSafe AI’s Jev model."
retrieval_nugget: "Simon Willison released llm-typesafe 0.1a0, an LLM CLI plugin that adds support for TypeSafe AI’s Jev model."
observed_at: "2026-09-22"
record_date: "2026-09-22"
date_kind: "observed_at"
why_it_matters: "Simon Willison released llm-typesafe 0.1a0, an LLM CLI plugin that adds support for TypeSafe AI’s Jev model. The supplied release note shows Jev invoked through `llm -m jev` for constrained tasks: a yes/no “noul” response with a probability, selection among supplied routing choices, and scoring against an ordered set of criteria. Examples include refund-request detection, support-team assignment, "
novelty: "notable"
verification_level: "source-linked"
signal_type: "release"
source_platform: "simonwillison.net"
topics: []
entities: []
related_patterns: []
source_url: "https://simonwillison.net/2026/Sep/22/llm-typesafe"
source_urls: ["https://simonwillison.net/2026/Sep/22/llm-typesafe"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:llm-typesafe-0-1a0-66b65b"
status: "published"
visuals: []
routes: {"html":"https://newruntime.com/signals/llm-typesafe-0-1a0-66b65b/","markdown":"https://newruntime.com/signals/llm-typesafe-0-1a0-66b65b.md","json":"https://newruntime.com/signals/llm-typesafe-0-1a0-66b65b.json"}
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
---

# Simon Willison released llm-typesafe 0.1a0, an LLM CLI plugin that adds support for TypeSafe AI’s Jev model

## Retrieval answer

Simon Willison released llm-typesafe 0.1a0, an LLM CLI plugin that adds support for TypeSafe AI’s Jev model.

Simon Willison released llm-typesafe 0.1a0, an LLM CLI plugin that adds support for TypeSafe AI’s Jev model. The supplied release note shows Jev invoked through `llm -m jev` for constrained tasks: a yes/no “noul” response with a probability, selection among supplied routing choices, and scoring against an ordered set of criteria. Examples include refund-request detection, support-team assignment, and bug-report reproducibility assessment. The release describes installation and API-key setup, but does not provide benchmark results, pricing, latency, or production reliability evidence.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- collection: [Raw Signals](https://newruntime.com/signals.json): Open every source-linked raw signal.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)