BrandKarma
start_deep_research
Spends one researched cluster from the plan. Researches a topic deeply into a durable dossier: four search engines are each asked their own questions, the best sources found are fetched and read, and the claims extracted from them are merged into one list with source URLs, dates, the points where sources disagree, and the questions the research could not settle. Runs as a background job — poll get_research_dossier or wait_for. Research a topical cluster once and let its articles draw different subsets; researching per article costs more and is what makes articles in one cluster sound alike. Pass planId + workstreamId to research a workstream (its title, goal, audience and brand keywords are used automatically, and the workstream's existing dossier is reused), or topic for a free-form one. A workstream-bound run also proposes articles from the dossier when it finishes.
Remote (network-hosted) · Requires an account with the vendor · OAuth
Other tools also called start_deep_research?
See providers with this name
Input Schema
{
"type": "object",
"properties": {
"brandId": {
"description": "Brand ID (ObjectId)",
"type": "string"
},
"topic": {
"description": "Free-form topic to research. Omit when passing planId + workstreamId.",
"type": [
"string",
"null"
],
"default": null
},
"planId": {
"description": "Content plan ID (ObjectId). Pass with workstreamId to research that workstream.",
"type": [
"string",
"null"
],
"default": null
},
"workstreamId": {
"description": "Workstream ID (GUID). Pass with planId.",
"type": [
"string",
"null"
],
"default": null
},
"audience": {
"description": "Who the resulting articles are for. Ignored for a workstream — its own audience is used.",
"type": [
"string",
"null"
],
"default": null
},
"keywords": {
"description": "Search terms the audience uses. Google's AI answer is fetched for the first three. Ignored for a workstream.",
"type": [
"array",
"null"
],
"items": {
"type": [
"string",
"null"
]
},
"default": null
},
"academic": {
"description": "Include arXiv. Only worth it for topics with an academic literature; noise for most B2B.",
"type": "boolean",
"default": false
},
"social": {
"description": "Include X discourse via Grok — what practitioners complain about and recommend.",
"type": "boolean",
"default": true
},
"aiAnswers": {
"description": "Include what Google's AI Mode already answers for the keywords, and whom it cites.",
"type": "boolean",
"default": true
},
"refresh": {
"description": "Re-run research from scratch on a dossier that is already ready.",
"type": "boolean",
"default": false
},
"language": {
"description": "ISO language code the research should target (e.g. 'de'). Overrides the brand default; sweep questions, claims and proposed ideas follow it.",
"type": [
"string",
"null"
],
"default": null
},
"country": {
"description": "ISO country code the research should target (e.g. 'DE'). Overrides the brand default.",
"type": [
"string",
"null"
],
"default": null
}
},
"required": [
"brandId"
]
}