Skip to main content

Introduction

Every page of this documentation is published in an AI-readable format, so an AI coding assistant — Claude Code, Cursor, GitHub Copilot, or any tool that can fetch a URL — can read the Comprehensive Motor Insurance guide and API reference directly and scaffold the integration for you: authentication, OTPs, quotes, photo uploads, policy issuance, and error handling. You stay in control of the code. The assistant writes the first draft against our guide and OpenAPI spec; you review it, test it in the Sandbox environment, and harden it before going live.

What to feed your assistant

Point your assistant at these pages. Appending .md to any page URL returns that page as plain Markdown.

Connect over MCP

If your assistant supports the Model Context Protocol, connect it to our documentation MCP server instead of pasting URLs — it gives the assistant search and retrieval tools over the entire documentation site:
MCP server URL

Ready-made prompt

Copy the prompt below into your assistant and let it read the docs before it writes any code.
Prompt for your AI assistant

Tips for good results

  • Always start in Sandbox. The flows mirror Production, but no real policies are issued — see Environments.
  • Keep credentials server-side. Yasmina APIs must be called from your backend; make sure generated code never ships the client secret or token to the browser.
  • Hold the assistant to the guide. The best-practice and branding guidelines in the guide are integration requirements, not suggestions — ask the assistant to implement them, then verify it did.
  • Review before Production. Treat the generated integration as a draft: run the full flow end to end in Sandbox and review the code before switching the base URL to Production.
Questions along the way? Contact us — we are happy to help.