---
type: "post"
id: "llm-openai-decisions-0-1a0-analysis-02836f"
slug: "llm-openai-decisions-0-1a0-analysis-02836f"
title: "Simon Willison released llm-openai-decisions 0.1a0"
description: "Thesis: A small integration plugin turns OpenAI’s Decisions API into a command-line workflow that can accept image-based decision queries."
retrieval_nugget: "Thesis: A small integration plugin turns OpenAI’s Decisions API into a command-line workflow that can accept image-based decision queries."
published_at: "2026-10-07"
updated_at: "2026-10-07"
record_date: "2026-10-07"
date_kind: "published_at"
topics: []
source_urls: ["https://simonwillison.net/2026/Oct/6/llm-openai-decisions"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:llm-openai-decisions-0-1a0-analysis-02836f"
status: "published"
visuals: []
editorial_provenance: {"schema_version":"newruntime-editorial-copy-v1","content_status":"source_grounded_final","final_copy_sha256":"sha256:182836df1cc780c701b9881204d3d73acff354a9afaff91218965e3f0a2e9179","reviewed_at":"2026-10-07T09:01:06.172Z","source_evidence_count":1,"verified_claim_count":3,"site_analysis_schema_version":"newruntime-site-analysis-v1","site_object_kind":"field_note","observed_fact_count":3,"implication_count":2,"watch_condition_count":1,"related_record_count":0}
analysis: {"schema_version":"newruntime-site-analysis-v1","object_kind":"field_note","thesis":"A small integration plugin turns OpenAI’s Decisions API into a command-line workflow that can accept image-based decision queries.","observed_facts":[{"text":"Simon Willison’s release note identifies the package as llm-openai-decisions 0.1a0 and gives `llm install llm-openai-decisions` as its installation command.","source_urls":["https://simonwillison.net/2026/Oct/6/llm-openai-decisions"]},{"text":"The note demonstrates an image attachment queried with gpt-6-luna and shows a predicate response containing a probability.","source_urls":["https://simonwillison.net/2026/Oct/6/llm-openai-decisions"]},{"text":"It also says the API supports yes/no, choice, and score question types.","source_urls":["https://simonwillison.net/2026/Oct/6/llm-openai-decisions"]}],"mechanism":"The plugin bridges the LLM command-line tool to the API, exposing structured decision requests through a familiar command interface rather than requiring users to build a separate client. The example indicates that an image can be supplied as an attachment and that the answer can be represented as structured data.","why_now":"The release follows the announcement of the Decisions API at OpenAI’s DevDay and provides an immediate route for experimenting with it in an existing LLM command-line workflow.","implications":["The integration lowers the friction of testing multimodal, structured decisions from scripts and command-line workflows.","This is an integration and example, not independent evidence of decision quality, robustness, or production readiness."],"evidence_boundary":"The supplied source is the plugin author’s release post and documents stated API capabilities, installation, and one example; it does not report independent benchmarks or systematic testing.","watch_conditions":["Watch for broader usage or independent tests that establish how reliably image-based decisions and the returned probabilities perform across real tasks."],"related_records":[],"new_branch_reason":"No prior New Runtime record was supplied, so this release begins a distinct analytical record focused on the plugin’s command-line bridge to the Decisions API."}
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"]}
routes: {"html":"https://newruntime.com/posts/llm-openai-decisions-0-1a0-analysis-02836f/","markdown":"https://newruntime.com/posts/llm-openai-decisions-0-1a0-analysis-02836f.md","json":"https://newruntime.com/posts/llm-openai-decisions-0-1a0-analysis-02836f.json"}
---

# Simon Willison released llm-openai-decisions 0.1a0

## Retrieval answer

Thesis: A small integration plugin turns OpenAI’s Decisions API into a command-line workflow that can accept image-based decision queries.

Thesis: A small integration plugin turns OpenAI’s Decisions API into a command-line workflow that can accept image-based decision queries.

Observed facts: Simon Willison’s release note identifies the package as llm-openai-decisions 0.1a0 and gives `llm install llm-openai-decisions` as its installation command. The note demonstrates an image attachment queried with gpt-6-luna and shows a predicate response containing a probability. It also says the API supports yes/no, choice, and score question types.

Mechanism: The plugin bridges the LLM command-line tool to the API, exposing structured decision requests through a familiar command interface rather than requiring users to build a separate client. The example indicates that an image can be supplied as an attachment and that the answer can be represented as structured data.

Why now: The release follows the announcement of the Decisions API at OpenAI’s DevDay and provides an immediate route for experimenting with it in an existing LLM command-line workflow.

Implications: The integration lowers the friction of testing multimodal, structured decisions from scripts and command-line workflows. This is an integration and example, not independent evidence of decision quality, robustness, or production readiness.

Evidence boundary: The supplied source is the plugin author’s release post and documents stated API capabilities, installation, and one example; it does not report independent benchmarks or systematic testing.

Watch conditions: Watch for broader usage or independent tests that establish how reliably image-based decisions and the returned probabilities perform across real tasks.

New branch reason: No prior New Runtime record was supplied, so this release begins a distinct analytical record focused on the plugin’s command-line bridge to the Decisions API.

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)