run_test
Compare ad creatives, prices, messages, offers, or pitches in an AI-simulated buyer audience to get each variant's metric, 95% margin, winner, lift, and clear/tie reading.
Instructions
Test anything from one spec on a prepared simulation: type = ad | message | price | offer | positioning | naming | landing | launch | pitch | email | creator_post | channel_mix; variants = the things to compare (ad creatives, message lines, prices, offer wordings, names, landing pages, launch posts with rounds, pitch scripts, emails); audience {segments, countries}; metric (default per type); budget {amount, cpm, currency}; rounds (launch). Returns one result shape for every type: each variant's metric with a 95% margin, the winner, the lift, whether it is clear or a tie, and how to read it. Background job.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"simulation_id": "<simulation_id>",
"spec": "<spec>"
},
"name": "run_test"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| run | No | ||
| spec | Yes | ||
| brand | No | ||
| simulation_id | Yes |