Read what each assistant actually said

The full answers to one question, side by side, with the sources each assistant cited - not a score, the words.

For: Anyone who wants to quote an assistant instead of describing a metric

Paste this into your assistant

Show me what each assistant answered to our question about the best tools for small agencies in the latest measurement, with the sources each one cited.

What happens

1. 01Finds the tracked question you mean.
2. 02Reads the full answers from the latest measurement day, one per assistant, with link targets removed and every cited URL listed.
3. 03Marks answers the assistant did not show at all (normal for Google AI Overviews) instead of treating them as failures.

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

The answers themselves, ready to quote in a report or a client call.

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