askround_run
Run all questions in a product file across AI providers to check whether a product is named, where it ranks, which rivals appear, and what claims and facts are returned.
Instructions
Ask every question of a product file (a prompt set) and return a brief per question: the runs naming the product and its best position per provider, its claims, the rivals, each fact with its answers' ids. detail: true returns every question's full report instead.
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": {
"file": "<file>"
},
"name": "askround_run"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| file | Yes | the product file (TOML); in this project: examples/askround.toml (3 questions), examples/modelado.toml (4 questions) | |
| runs | No | ||
| detail | No | every question's full report | |
| extract | No | ||
| max_cost | No | refuse, before any call, a run estimated above this (USD) | |
| providers | No | only these providers (default: every one with a key) | |
| background | No | start it as a job and return at once; read it with askround_job |