How we nudge models using URLs

Anthropic and OpenAI's models now read URLs directly in the prompt. You can point them at a spec, a blog post, or a PR and the model treats it as part of its context window — not as a link to click, but as something to reason about. That changes how we write for models, not just for people.

The trick is that the model doesn't just fetch the page; it parses it and weaves the content into its next response. Write the URL into the prompt the way you'd write a paragraph. The model reads it like a colleague who shows up to the table with a document.

This matters because it means your docs, your APIs, your specs — they're no longer behind a click. They're living context. You stop writing for browsers and start writing for the models that will read them. And the ones you write for models will serve people better, because the models are the first readers and the last filter.

Why this matters for us: the tools we build and the docs we write need to be legible to models — not just to humans. If your spec is only readable by people, it's already outdated.