TwinsGong
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.
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.
- Calls, recordings and transcripts
- Speakers, topics and trackers
- Deal and account links
- Users and teams
- Search and filters
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.
Validate every action
The twin checks what the agent sends the way Gong 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 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.
Swap the address. Your agent code stays the same.
Replace the live Gong endpoint with the twin’s. Everything your agent already does keeps working, on data that is yours to break.
{
"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.
Read the guide: How to test AI agents before production →