A proposal for inline LLM instructions in HTML based on llms.txt How do you tell an AI agent what it needs to do when it hits a protected page? Most systems rely on external documentation or pre-configured knowledge, but there's a simpler approach. What if the instructions were right there in the HTML response? llms.txt is an emerging standard for making content such as docs available for direct consumption by AIs. We’re proposing a convention to include such content directly in HTML responses as <script type="text/llms.txt"> . Link to heading Our use case Vercel protects preview deployments behind Vercel Authentication by default. This prevents random users from accessing your private, under-development software. However, it also prevents coding agents like Cursor, Devin, or Claude Code from being able to directly access your deployments.…