Find missing topics on a page
Compare observed search queries with page text to identify missing topics and where to add them.
When to use this workflow
“Find the questions this page does not answer.”
Before fetching
Prepare the URL, current page text, relevant prompts, platform, and period. Use a supplied file or the agent’s browsing capability for the page text and record its retrieval time.
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 observed search queries
Read configured prompts separately from queries actually issued by the AI. If fanout_availability is missing, unavailable, or unknown, do not conclude that no queries were issued.
orc prompts get YOUR_PROMPT_ID --json
orc fanout-queries list --type search --prompt-id YOUR_PROMPT_ID --start-date 2026-09-01 --end-date 2026-09-07 --json2. Map query intent to page passages
For each query, have the agent record the required answer, matching passage, and missing explanation. Recurrence measures this observation set, not total market search demand.
3. Select topics to add
Prioritize evidenced gaps and choose an addition to an existing section or a new section. Do not call the page audit complete when its text could not be retrieved.
Deliverable
Deliver query text and IDs, intent, matching passages, missing topics, insertion points, and priority reasons.
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.