Getting started

Look up one source

Answer a question about one URL or domain with its observed retrievals, citations, and scope.

When to use this workflow

“How often is this URL cited?”

Before fetching

Determine whether the question concerns one URL, a host, or a whole domain. State the dates and platform when the request omits them.

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. Resolve the source at the requested grain

Select the exact URL from the list. Use domains list for domain questions; do not report one URL’s count as a domain total. Finish pagination before concluding that the source is absent.

orc sources urls list --start-date 2026-09-01 --end-date 2026-09-07 --json
orc sources domains list --start-date 2026-09-01 --end-date 2026-09-07 --json

2. Fetch scoped citation counts

Filter to the requested URL. Keep retrieval observations separate from explicit citations. Only when asked which prompts use it, fetch the selected prompt’s answers and match their citation URLs.

orc sources citations list --group-by url --filter[url] 'https://example.com/page' --start-date 2026-09-01 --end-date 2026-09-07 --json
orc answers list --prompt-id YOUR_PROMPT_ID --json

Deliverable

Lead with the number, followed by the URL, dates, platform, and cohort. If you inspected answers, include the number read and their IDs.

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.