Specify how a small tool should accept your input

Published by Simon Willison

This credits the original publisher. Better Loop membership or a shared assessment is not implied.

The public work

Willison describes creating a QR decoder when he lacked his phone during a meeting. The linked conversation shows an initial URL-based implementation followed by a request for file selection, drag-and-drop and pasted images.

What to notice

Check the interaction as well as the nominal capability: a tool that solves the right problem may still accept the wrong input form.

Keep the context

This is an author-documented utility with a public conversation, not an independently tested decoder. The original generated code and current browser compatibility were not executed or audited here.

AI use: Documented in the source.

The source identifies Claude Artifacts, and the public conversation shows the requested interaction changes. The exact model version is unspecified.

A useful public example is not an assessment of a reader, a publisher or a Better Loop member.

Authored practice suggestion

Try the idea.
Check your own work.

Use material you are allowed to work with. This suggestion is preparation; it does not record a completed task or an improvement.

A prompt to adapt privately

Choose a public QR image with a known payload. Describe the input method you actually need, then ask for a minimal decoder interface. Review whether file selection, image paste or drag-and-drop is supported as requested, and compare the decoded text with the known payload.

A check to adapt

The requested input method is supported and the decoded text exactly matches the known public payload.

Open a related practice brief

Private practice needs no account. Your configured model provider may process the evidence you select.

See the full skill-to-sharing flow

Another way into the work.

Compare audio and visuals before summarizing video

OpenAI’s notebook processes a real DevDay recap into frames and audio, then prints summaries and answers from visual input, audio-derived text, and both together. The differing outputs make missing context visible.

Published byOpenAI Cookbook / Juston Forte

Curated public exampleGuide

Math & science

Selecting peaks in a recorded ECG signal

The SciPy example applies height, spacing, prominence and width conditions to a recorded ECG segment. It displays selected peaks, interval arrays and property values, making each filtering choice inspectable.

Published byThe SciPy community

Curated public exampleNotebook

Everyday work

Control summary detail without confusing length and quality

OpenAI summarizes a Wikipedia article about artificial intelligence using different chunk counts and a detail parameter. The notebook prints summaries and their lengths, including a recursive variant that supplies earlier summaries as context.

Published byOpenAI Cookbook