DisQ
Ai For Agents

LLMs.txt

How to get AI tools like Cursor, Windsurf, GitHub Copilot, ChatGPT, and Claude to understand the DisQ API (base URL, versioning, authentication, and available endpoints).

What is LLMs.txt?

LLMs.txt is a structured documentation format for large language models (LLMs). DisQ exposes LLMs.txt files so AI tools can reliably reference the public API: base URL, versioning, authorization header usage, and currently documented endpoints for Users and Bots.

These files are optimized for AI consumption and contain structured information about endpoints and usage patterns already present in the DisQ documentation.

Available routes

We provide LLMs.txt routes to help AI tools access our documentation:

  • /llms.txt – Structured overview of the API (base URL, versioning, auth header requirement, key endpoints)
  • /llms-full.txt – Expanded reference with full endpoint examples and field structures

Choosing the Right File

Most users should start with /llms.txt – it contains the essential DisQ API information suitable for standard LLM context windows. Use /llms-full.txt when you need the extended endpoint examples.

Important usage notes

@-symbol must be typed manually – When using tools like Cursor or Windsurf, type the @ symbol by hand in the chat interface. Copy‑pasting can prevent the tool from detecting it as a context reference.

Usage with AI Tools

Cursor

Reference the DisQ LLMs.txt URLs so the AI can ground answers in the documented API.

How to use:

  1. Mention the LLMs.txt URLs when asking about an endpoint or request format
  2. Add the URLs to project context using @docs (e.g. @docs https://docs.disq.ink/llms.txt)

Read more about Cursor Web and Docs Search

Windsurf

Windsurf can pull in the DisQ LLMs.txt files for API‑aware assistance.

Using LLMs.txt with Windsurf:

  • Use @docs to reference the LLMs.txt URLs
  • Optionally add workspace rules pointing to them

Read more about Windsurf Web and Docs Search

Other AI Tools

Any AI tool that supports LLMs.txt can use these routes to better understand the DisQ API.

Prompt examples (ChatGPT, Claude, etc.)