Skip to main content
Your content has two audiences: humans and AI. Not long ago, someone who needed help with your product would start with your docs. If they couldn’t find an answer, they might open a support ticket or try another product. That pattern has changed. People now ask tools such as ChatGPT, Claude, Perplexity, and your Mintlify assistant for answers grounded in your content. Developers also use coding agents such as Claude Code and Cursor to understand and build with your product. Your content must still work well for humans. But you also need to consider the AI that mediates between your content and your users. The good news is that agent-friendly content is usually better for people too. Clear pages, explicit context, consistent terms, and a tight focus help every reader. This course also covers the few considerations that are specific to agents.

​
Who this is for

Developers, technical writers, and product teams who maintain content. Some lessons focus on Mintlify, but the principles apply to any platform. You don’t need a background in AI or machine learning, just an interest in making your content work well for anyone (or anything) that reads it.

​
Lessons in this course

  1. How agents read your content—How agents find and fetch your pages, and the technical problems that make them fail silently.
  2. Write content agents can use—Writing habits that make each page reliable context for agents.
  3. Help agents find and read your content—Configure llms.txt, Markdown output, your MCP server, and skill.md.
  4. Give agents your team’s conventions—Write instruction files for the AI tools that help your team write docs.
  5. Test whether agents can use your content—Build a repeatable question set and check your technical setup.
  6. Protect private and sensitive information—Separate discovery from access control and test what each audience can retrieve.
  7. Keep content agent-friendly over time—Use analytics and agent feedback to keep content accurate as your product changes.

​
Agent-friendly content checklist

Use this as a quick reference.

​
Content

  • Every page makes sense without reading adjacent pages
  • Page titles are specific enough to match user questions (“Configure rate limits for API requests” instead of “Advanced configuration”)
  • Every page has a description that names the task and topics it covers
  • Headings make sense without surrounding context
  • Each page covers one topic or task
  • Terminology is consistent, with one name per concept

​
Examples and references

  • Code examples are complete and runnable
  • Placeholder values are clear and explain what to substitute
  • Cross-references name what they link to. No “click here,” “the above,” or similar

​
Configuration

  • The description in docs.json explains what your product does
  • Deprecated, internal, and pre-release pages are marked hidden: true or noindex: true
  • Your MCP server is easy for users to connect, for example through the contextual menu
  • .mintlify/AGENTS.md defines audience, terminology, and content type rules for Mintlify’s agent
  • Private content is protected by authentication, not just hidden
  • mint score passes the checks that matter for your site

​
Evaluation

  • A saved set of user questions covers lookup, tasks, troubleshooting, ambiguity, and unsupported requests
  • Expected facts and supporting sources are recorded for each question
  • Each run records which agent was tested and how it accessed your content
  • The question set runs after major content, terminology, configuration, or access changes

​
Ongoing maintenance

  • Assistant analytics and agent feedback are reviewed regularly
  • Content is updated alongside product changes
  • Agent instruction files are updated when terminology changes
Next up: How agents read your content—how agents find and fetch your pages.