Read an A/B test
experiment_resultsVisitors exposed and converted per variant (a conversion counts only at or after the visitor's first exposure), each variant's rate with its 95% interval, chance to beat the control, the lift and its interval, a sample ratio check, and the verdict: keep running, winner, control wins, no difference, or a broken split. Never call a winner the verdict does not. Without a key, every test in the workspace, running first. Free.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "experiment_results"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| key | No | ||
| site | No |