Twins/Salesforce

A Salesforce twin for testing AI agents.

Test agents that read and update the CRM. The same API and MCP calls, the same validation and permissions, and nothing changes in your real org.

Meet the Salesforce twin.

A stateful copy of Salesforce, 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.

What your agent can do

  • Accounts, contacts, leads and opportunities
  • Field validation and required fields
  • Stages and workflow rules
  • SOQL queries
  • Permissions and sharing
  • API limits

Seeded state

Every run starts from a company that already has history. We seed:

  • Accounts with contacts and history
  • Open opportunities at every stage
  • Activities, notes and tasks
  • Users with profiles

Use Salesforce in staging, without using production.

  1. 01Validate every actionThe twin checks what the agent sends the way Salesforce would: required fields, permissions, rate limits, malformed input. Mistakes fail here, not in your account.
  2. 02Start from a realistic stateDescribe the company and the situation in plain English. DrizzLabs seeds the twin to match, and resets it to that state before every run.
  3. 03Replay tasks across toolsThe Salesforce 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.

Point your agent at the twin.

Swap the live tool’s address for the twin’s. Your agent code stays the same.

  • Accounts and opportunities
  • Field validation
  • SOQL
  • Permissions
  • MCP and REST on the same data
  • One-call reset

{
  "mcpServers": {
    "salesforce": {
      "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 deal in Salesforce has the email threads, meetings, Slack channel and Gong calls behind it, so an agent that updates the stage can be checked against what actually happened.

Thirty minutes with a founder

Run your agent on the Salesforce twin.