We create SDK examples, maintain GitHub repositories, run communities, and answer implementation questions.
The developer may now ask an AI agent to research a library, understand an API, write an integration, or debug an error.
That means your documentation can become an input to an AI agent before it ever reaches a developer.
Developer ↓ AI Assistant ↓ Docs / GitHub / API Reference ↓ AI interprets information ↓ Code ↓ Developer reviews
Which package? How do I install it? Where does the API key go? Can I use it in the browser? What happens when authentication fails? What's the response format?
const user = await client.users.create({ name: "Alex", email: "alex@example.com" });
Required fields Optional fields Response shape Validation errors Authentication requirements
What is this? How do I install it? How do I use it? What does it support? What are its limitations? Where are the detailed docs?
It's that an AI agent can use that documentation while completing a software task.
Read docs ↓ Choose API ↓ Generate code ↓ Run code ↓ Read error ↓ Search docs ↓ Fix code
Your documentation may now need to work for the developer and the AI assistant helping them.
"Is our developer experience clear enough for both humans and machines to use correctly?"