Who each assistant picks when asked to choose

For questions like which is best or who is favored: a clear pick, a toss-up, no call or a refusal - per assistant, with the sentence it rests on.

For: Anyone asking the assistants for a judgment and reporting what they concluded

Paste this into your assistant

For our questions that ask for a judgment, show what each assistant concluded - a clear pick, a toss-up, no call or a refusal - with the sentence each verdict rests on, and total the picks per assistant.

What happens

1. 01Reads the verdict for every question that asks for a judgment, one per assistant.
2. 02Takes the conclusion of the whole answer, not the first name after a heading, and quotes the sentence it rests on.
3. 03Totals picks, toss-ups, non-answers and refusals per assistant.

Tools it calls

• getVerdictMatrixread only

  For questions that ask for a judgment (who is favored, which is best), what each assistant concluded: a prompt x engine grid of favorite / tossup / no_call / refused, the favored entity and its group (e.g. party), and the sentence that carries the verdict, plus totals per engine. Defaults to the latest measurement day.

What you end up with

A question-by-assistant grid of verdicts you can check against the quotes.

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. How to connect.