TwinsLinear
A Linear twin for testing AI agents.
Test agents that triage and update issues. Teams, issues and states your agent can work through, without touching your real backlog.
A stateful copy of Linear, 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.
- Issues, states and cycles
- Projects and teams
- Assignees, labels and priorities
- Comments and relations
- Permissions
Every run starts from a company that already has history. We seed:
- Teams with their own workflows
- A backlog and a cycle in progress
- Projects with milestones
- Users and labels
Use Linear in staging, without using production.
Validate every action
The twin checks what the agent sends the way Linear 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 Linear 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 Linear endpoint with the twin’s. Everything your agent already does keeps working, on data that is yours to break.
{
"mcpServers": {
"linear": {
"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 Linear issue links to the GitHub pull request that closes it and the Slack thread where it came up.
Read the guide: How to test AI agents before production →