Sentiment

also known as: mention sentiment

How positively, neutrally or negatively an AI answer characterizes a named brand, a qualitative read that matters as much as whether the brand was mentioned at all, since being named in a comparison as the worse option is a different outcome than being recommended. It is derived from the answer’s actual phrasing around the mention, not assumed from mention count alone.

In AI Search API

Sentiment is not a field the API returns; it is something you compute from the answer. answer.text and answer.markdown ship in every Envelope, so you run your own sentiment pass over exactly what the surface said about a brand, keeping the scoring logic yours to tune and audit. A brand can read positive in one surface’s answer and neutral in another’s for the identical prompt, so sentiment only makes sense per surface, never averaged across incompatible engines.

Envelope excerpt, the answer you score
"answer": {
  "text": "YourBrand is a strong pick for teams that…",
  "markdown": "…"
}

Related terms

See it in the product

Every definition here is enforced in the Envelope contract. Run a capture and read the fields yourself.