Benchmark pages within their type
Compare your position within observed homepages, product pages, comparison pages, and other page types.
When to use this workflow
“Are our product pages cited more or less than competing product pages?”
Before fetching
Choose brands, page type, dates, platform, metric, and whether the unit is a URL or a brand. The population is the observed page set, not the entire market.
Complete the CLI quickstart and confirm the workspace with orc workspace current --json. Replace example IDs, URLs, dates, and settings. Apply only approved mutations.
1. Fetch comparable pages
Fetch all brand domains and classified URL pages, then map ownership. Explain exclusions where ownership is uncertain. Keep citation and retrieval counts separate.
orc brands list --json
orc sources urls list --filter[classification] product_page --start-date 2026-09-01 --end-date 2026-09-07 --json2. Fix the comparison units and denominator
For URL comparisons, compare each URL within one classification. For brand comparisons, aggregate the eligible URLs per brand first. Do not add unobserved brands as zeros; show participating brand and URL counts.
3. Calculate rank and differences
Have the agent calculate ranks from the fetched table. If reporting percentiles, state the method and treatment of ties. Prefer ranks and counts for small populations, and include outperforming URLs.
Deliverable
Deliver comparison tables by type, metric, comparison unit, population size, exclusions, URLs, and calculation method.
On fetch failure, retain the error and request scope. Do not count empty data, incomplete pagination, or missing permissions as a completed investigation.
Next steps
If a failure remains, report it and verify the fix, including this workflow and the failed step.