Split the names in the answers by any group

Party, country, segment, partner or not - group the names the assistants mention and compare the shares per assistant.

For: Analysts comparing how evenly the assistants present a market

Paste this into your assistant

Group the people named in our answers by party and compare the shares for each assistant. Leave out background mentions, and list anyone whose party is still unknown.

What happens

1. 01Reads the names with their attributes, such as party, office or country.
2. 02Groups them per assistant and attribute value, counting only answers where they are a real option rather than background.
3. 03Lists names with the attribute missing, so you can fill it in before trusting the shares.

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

Shares per group and assistant, with no name matching on your side.

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.