Skip to main content
Answer: “How often are we mentioned compared with the brands measured in this project, and does the pattern differ by platform?”

​
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_project to read the configured brand terms and competitor context.
  2. Request entity-level mention coverage for the configured brand and competitors, grouped by platform.
  3. Use list_mention_statements for selected brands to inspect the supporting answers. Follow the returned cursor for more statements.

​
Build the report

Create one row per brand entity and platform, retaining data.rows[].entity_or_bundle, group_by_values, and estimate. Display coverage with the returned interval and a note for limited rows. Follow with a small set of supporting statements and their sources. Do not add alias coverage percentages together. A response can mention several aliases, and this request reports entities. Use response handling to keep entity rows separate from headline brand-term coverage. For change over time, use comparable runs and the comparison guide. The paired contrast tool in this edition does not test mention coverage, so this recipe does not promise that significance test. Reference: mention scores, statements.