Who the assistants actually recommend

Not just who is mentioned - who is presented as the pick, and who only appears as background.

For: Teams that need to separate a recommendation from a passing mention

Paste this into your assistant

Which companies and people do the assistants recommend in our answers, as opposed to mentioning them in passing? Rank them by how often they are recommended and show it per assistant.

What happens

1. 01Lists the names found in the answers with how each answer treats them: recommended, neutral, background or criticized.
2. 02Counts only the recommendations, per assistant, with how often each name comes first.

Tools it calls

• listEntitiesread only

  People, organizations, media, places and products named in the assistants' answers, with their aliases, attributes (such as party or office) and how many answers name each one. Use it to find entity IDs and to check attributes before getEntityMetrics or updateEntity.

• getEntityMetricsread only

  How often entities are named, grouped the way you ask - by engine, topic, entity or an attribute such as party. Returns presence (share of answers naming the group), share of all named entities, average rank and how often the group is named first. Use groupBy ["engine", "attribute:party"] with entityType "person" for party shares per assistant.

What you end up with

A ranking of who the assistants push, separate from who they merely name.

Answer analysis switched on for the project - it reads every answer with a model, so the Scorra team turns it on per project. Ask us. MCP is included from Growth up, and during the 7-day trial. How to connect.