What changed in the answers since last time

Two measurement days, the same questions: who got named, who dropped out, which sources changed.

For: Teams reporting week over week who need the reason, not just the delta

Paste this into your assistant

Compare the answers from our last two measurement days for our five most important questions. Who is named now that was not before, who dropped out, and which cited sources changed?

What happens

1. 01Picks the questions and reads the answers for both days, with their citations.
2. 02Compares them assistant by assistant, so a change on one engine is not lost in the others.
3. 03Quotes the sentences that changed instead of paraphrasing them.

Tools it calls

• listPromptsread only

  The questions being tracked for a project, with their intent and topic tags. Read this before proposing new prompts - a duplicate takes a prompt slot from the plan and measures the same question twice, every day, for nothing.

• listAnswersread only

  The full answers the AI assistants gave to tracked prompts, with the sources each one cited. Use it to read what a model actually said - quotes, names, recommendations - rather than the aggregated metrics. Defaults to the latest measurement day; pass `from`/`to` for history, and page through results with `cursor`. For large projects start with `includeText: false` or a `maxChars` limit.

What you end up with

A before-and-after for each question, with the evidence in the assistants' own words.

MCP is included from Growth up, and during the 7-day trial. How to connect.