Twins/Gong

A Gong twin for testing AI agents.

Test agents that read calls, pull out next steps and update the deal. Recorded calls and transcripts, with no real customer on the line.

Meet the Gong twin.

A stateful copy of Gong, 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

  • Calls, recordings and transcripts
  • Speakers, topics and trackers
  • Deal and account links
  • Users and teams
  • Search and filters

Seeded state

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

  • Calls across every open deal
  • Transcripts with speakers and timestamps
  • Trackers and topics
  • Scorecards

Use Gong in staging, without using production.

  1. 01Validate every actionThe twin checks what the agent sends the way Gong 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 Gong 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.

  • Calls and transcripts
  • Speakers and topics
  • Deal links
  • Users and teams
  • One-call reset
{
  "mcpServers": {
    "gong": {
      "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.

Every call in Gong belongs to a deal in Salesforce or HubSpot, and to a contact who also has email threads and calendar invites.

Thirty minutes with a founder

Run your agent on the Gong twin.