Build with AI agents
These docs are written to be read by coding agents (Claude Code, Codex, Cursor) and AI chats as much as by people. Point your agent at the sources below rather than letting it guess the API.
Every page in Markdown
Add .md to the URL of any page of these docs to get it as Markdown, without navigation or styling. The Copy page menu at the top of every page copies that Markdown, or opens the page in ChatGPT or Claude.
curl https://zenhost.com/developers/ai-agents.mdllms.txt
Following the llms.txt convention, https://zenhost.com/developers/llms.txt lists every page with a one-line summary and its Markdown URL. https://zenhost.com/developers/llms-full.txt holds the whole documentation, API reference included, in a single file: give it to an agent that should read everything before it writes code.
https://zenhost.com/developers/llms.txt
https://zenhost.com/developers/llms-full.txtOpenAPI spec
The OpenAPI 3.1 document at https://app.zenhost.com/api/v1/openapi.json is the machine-readable contract of every endpoint. Have your agent generate a typed client from it or check each request and response against it, instead of inferring shapes from examples.
A prompt to start with
Paste this into your agent at the start of an integration, then describe what you are building.
I am building an integration with the ZenHost Public API.
Before writing any code, read the full documentation: https://zenhost.com/developers/llms-full.txt
The OpenAPI spec is the source of truth for every request and response: https://app.zenhost.com/api/v1/openapi.json
Follow the documented behaviour for authentication (OAuth 2.0 with PKCE and rotating refresh tokens), errors, rate limits and pagination. Write Restrictions through Restriction Batches. Read the client secret and tokens from environment variables, never from the code.