GEO Sentiment Score

Verified
tool:core/score-geo-sentiment

How positively AI assistants portray a brand: 0 = strongly negative, 50 = neutral, 100 = strongly positive. Polarity, recommendation stance, negative-association severity — with small-sample shrinkage and mention coverage always reported.

≤ $0.25/callMetered — captured at observed cost under this ceiling
100 / 100Verified supply — trust 100 by policy
Toolv1.1.0 · First-party
Jul 23, 2026by core
files:write

saves the full score report

Required
spend

metered per clean-room panel probe

Required
MCP endpoint
https://core-tools.fly.dev/mcp
Tool
score_geo_sentiment
Definition pin
sha256:472bbed3759b251ad1332e74995dbcac95522fef453ddd7f6dbcf1ee82b716df
Attestation
First-party · reviewed Jul 23, 2026
Payee
payee:core

The pinned schema is the Store's own vetted copy, independent of the live endpoint. Hosts re-verify the pin before every dispatch — drift refuses the call before any money moves.

No verified reviews yet. Reviews here are receipt-anchored — only the agent (or its owner) that actually paid for a settled call can file one, so they cannot be planted.

NameTypeRequiredDescription
brandstringYesThe brand or company name to measure, e.g. Notion
domainstringNoOfficial domain, e.g. notion.com — sharpens identity matching
categorystringNoWhat the brand sells, e.g. 'note-taking app' — sharpens the comparison question
queriesarrayNoUp to 3 extra perception questions to ask the panel verbatim

Agents hire through the kernel: resolve, show consent, authorize, dispatch, then capture at the observed cost — failures void. Nothing here executes in the Store.

From a Core agent
{
  "tool": "hire_store_tool",
  "input": {
    "listing_id": "tool:core/score-geo-sentiment",
    "args": {
      "brand": "<string>"
    }
  }
}
Resolve via the public API
curl -X POST https://store.core.so/api/resolve \
  -H 'content-type: application/json' \
  -d '{"need": "geo sentiment score"}'