TwinsGoogle Drive
A Google Drive twin for testing AI agents.
Test agents that find, read, create and share files. Folders and documents your agent can work in, with nothing shared from a real Drive.
A stateful copy of Google Drive, built for testing agents.
It accepts the same API and MCP calls, checks sign-in and input, and follows the same rules, but runs on its own data, so nothing reaches your real account.
- Files and folders
- Create, copy, move and trash
- Sharing and permissions
- Search and metadata
- Revisions and export to other formats
Every run starts from a company that already has history. We seed:
- A shared drive for each team
- Folders with real documents
- Permissions per person
- Revision history
Use Google Drive in staging, without using production.
Validate every action
The twin checks what the agent sends the way Google Drive would: required fields, permissions, rate limits, malformed input. Mistakes fail here, not in your account.
Start from a realistic state
Describe the company and the situation in plain English. Drizz seeds the twin to match, and resets it to that state before every run.
Replay tasks across tools
The Google Drive twin shares its people, customers and history with the other twins, so a task that touches three tools runs the way it would at work.
Swap the address. Your agent code stays the same.
Replace the live Google Drive endpoint with the twin’s. Everything your agent already does keeps working, on data that is yours to break.
{
"mcpServers": {
"google-drive": {
"type": "http",
"url": "<twin MCP endpoint>",
"headers": { "Authorization": "Bearer <token>" }
}
}
}REST works on the same data. Both are reset with one call.
Connected to the rest of the company.
A file in Drive is attached to the email that sent it, the meeting it was presented in and the deal it belongs to.
Read the guide: How to test AI agents before production →
17 of 20 runs passed. 3 broke a rule.