TwinsHubSpot
A HubSpot twin for testing AI agents.
Test agents that update contacts, move deals and log activity. A private CRM with the same objects, properties and rules as the real one.
A stateful copy of HubSpot, 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.
- Contacts, companies, deals and tickets
- Properties and validation
- Pipelines and stages
- Associations
- Timeline events, notes and search
Every run starts from a company that already has history. We seed:
- Companies with contacts and history
- Deals in every pipeline stage
- Open tickets
- Users and teams
Use HubSpot in staging, without using production.
Validate every action
The twin checks what the agent sends the way HubSpot 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 HubSpot 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 HubSpot endpoint with the twin’s. Everything your agent already does keeps working, on data that is yours to break.
{
"mcpServers": {
"hubspot": {
"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.
Deals in HubSpot share their contacts with Gmail, Calendar and Gong, and their tickets with Jira and Slack.
Read the guide: How to test AI agents before production →