Skip to main content
Answer: “Which editorial or expert sources support our brand and competitors in these answers?”

​
Prepare the scope

Use list_projects and list_runs to choose the project and completed run. Check readiness, then call get_results_stability for the same run and supported filters. For each measurement, preserve the scope, returned confidence interval, and row-quality fields. See run selection and decision-grade measurement. The JSON examples below are MCP tools/call parameter objects. Replace ID placeholders and sample selections with values discovered in your account.

​
Retrieve the evidence

  1. Call get_grounding_sources for the brand subset you intend to review.
  2. Call compare_grounding_sources with the selected brand labels to separate shared and brand-specific sources.
  3. For a candidate domain, use get_brands_grounded_by_source and inspect relevant statements or page evidence.

​
Build the report

For each candidate, show the source domain, brands it supports, the returned estimate and interval, and a short explanation grounded in the answer evidence. Retain the requested denominator when labeling the source metric. Treat these as candidates for editorial, expert, or influencer research. A cited domain does not identify a specific influencer, their audience size, contact details, or commercial availability. Add those details only after separate verification; they are not fields returned by this workflow. Reference: grounding sources, source comparison, brands by source.