---
type: "post"
id: "llm-typesafe-0-1a0-analysis-24b1a3"
slug: "llm-typesafe-0-1a0-analysis-24b1a3"
title: "Simon Willison released llm-typesafe 0.1a0, an LLM CLI plugin that adds support for TypeSafe AI’s Jev model"
description: "llm-typesafe 0.1a0 turns Jev into a CLI-accessible component for constrained classification and scoring steps in LLM-based workflows."
retrieval_nugget: "llm-typesafe 0.1a0 turns Jev into a CLI-accessible component for constrained classification and scoring steps in LLM-based workflows."
published_at: "2026-09-22"
updated_at: "2026-09-22"
record_date: "2026-09-22"
date_kind: "published_at"
topics: []
source_urls: ["https://simonwillison.net/2026/Sep/22/llm-typesafe"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:llm-typesafe-0-1a0-analysis-24b1a3"
status: "published"
visuals: []
editorial_provenance: {"schema_version":"newruntime-editorial-copy-v1","content_status":"source_grounded_final","final_copy_sha256":"sha256:b55e90d60bcf56e2bda4b52a69e5dc47b67017e4861fc159741515c9e1cd4e47","reviewed_at":"2026-09-22T18:00:52.204Z","source_evidence_count":1,"verified_claim_count":2,"site_analysis_schema_version":"newruntime-site-analysis-v1","site_object_kind":"field_note","observed_fact_count":2,"implication_count":2,"watch_condition_count":2,"related_record_count":0}
analysis: {"schema_version":"newruntime-site-analysis-v1","object_kind":"field_note","thesis":"llm-typesafe 0.1a0 turns Jev into a CLI-accessible component for constrained classification and scoring steps in LLM-based workflows.","observed_facts":[{"text":"The release note says llm-typesafe 0.1a0 is a new plugin for LLM that adds support for TypeSafe AI’s Jev model.","source_urls":["https://simonwillison.net/2026/Sep/22/llm-typesafe"]},{"text":"The supplied examples cover a probability-returning yes/no “noul” query, choice-based support routing, and score-based bug-report reproducibility assessment.","source_urls":["https://simonwillison.net/2026/Sep/22/llm-typesafe"]}],"mechanism":"The mechanism is constrained task framing: an operator supplies a question plus an answer type and, where relevant, an explicit choice set or scoring rubric; Jev returns a result that can be consumed by a downstream rule or workflow.","why_now":"Why now is that the plugin exposes this interface inside an established command-line tool, making it easy to place beside pipes, files, and operational scripts.","implications":["The first implication is that teams can prototype routing, intake review, and quality triage as small, inspectable CLI stages rather than building a bespoke model integration first.","A second implication is that instructions can encode precedence rules, such as choosing billing when billing and technical signals coexist."],"evidence_boundary":"The evidence boundary is that the public release supplies examples and setup instructions, not comparative accuracy, calibration, latency, price, scale limits, or evidence of production performance.","watch_conditions":["The first watch condition is whether independent users publish evaluations showing reliable behavior across ambiguous, adversarial, and domain-specific inputs.","Watch for documentation or user reports on error handling, confidence thresholds, and integration behavior in automated workflows."],"related_records":[],"new_branch_reason":"This begins a distinct analytical record because the supplied material identifies a new tool release, while it supplies no prior New Runtime record whose analysis can be extended."}
routes: {"html":"https://newruntime.com/posts/llm-typesafe-0-1a0-analysis-24b1a3/","markdown":"https://newruntime.com/posts/llm-typesafe-0-1a0-analysis-24b1a3.md","json":"https://newruntime.com/posts/llm-typesafe-0-1a0-analysis-24b1a3.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

llm-typesafe 0.1a0 turns Jev into a CLI-accessible component for constrained classification and scoring steps in LLM-based workflows.

llm-typesafe 0.1a0 turns Jev into a CLI-accessible component for constrained classification and scoring steps in LLM-based workflows.

The release note states that llm-typesafe is a new plugin for Simon Willison’s LLM tool and that it adds support for TypeSafe AI’s Jev model. It documents installation with `llm install llm-typesafe`, API-key configuration, and invocation through `llm -m jev`. It also shows a “noul” example returning `{"type": "noul", "noul": 0.99}` for a refund-request question. A second example supplies named choices for billing, technical, and other support routing; a third supplies ordered reproducibility criteria for scoring a report.

The mechanism is constrained task framing: an operator supplies a question plus an answer type and, where relevant, an explicit choice set or scoring rubric; Jev returns a result that can be consumed by a downstream rule or workflow. This moves the useful unit from open-ended assistant prose to a bounded decision interface. Why now is that the plugin exposes this interface inside an established command-line tool, making it easy to place beside pipes, files, and operational scripts.

The first implication is that teams can prototype routing, intake review, and quality triage as small, inspectable CLI stages rather than building a bespoke model integration first. A second implication is that instructions can encode precedence rules, such as choosing billing when billing and technical signals coexist. The evidence boundary is that the public release supplies examples and setup instructions, not comparative accuracy, calibration, latency, price, scale limits, or evidence of production performance. The first watch condition is whether independent users publish evaluations showing reliable behavior across ambiguous, adversarial, and domain-specific inputs.

This begins a distinct analytical record because the supplied material identifies a new tool release, while it supplies no prior New Runtime record whose analysis can be extended.

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: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- 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)