Triage content gaps
The Content gaps tab is the single home for "content readers want but cannot find." It has two sections, one clustered and one raw, and lets you act on each row directly.
Before you begin
You need a published site with reader traffic, either through its AI search or chat widget, or through the site search box.
Open the tab
Go to Analytics in the sidebar.
Open the Content gaps tab.
The Zero-result rate card on the AI queries and crawler activity tab links here too, and turns amber above 30%.
Before you publish anything, the tab is still there and explains itself: "No published targets yet. Publish a map to start collecting the reader questions that surface content gaps." Gaps are derived from what readers do on a live site, so there is nothing to cluster until one exists.
Suggested gaps
The Suggested gaps section lists clusters that weekly gap detection found. It draws on two evidence streams: reader AI questions that returned no more than one result or drew a thumbs-down, and keyword searches from the site search box that returned nothing. It clusters similar wordings together, discards off-topic noise, and proposes a topic title for the rest. Each row shows:
The suggested topic title (or the representative query, if no title was generated).
How many queries are in the cluster and the representative query text.
A confidence badge (Strong, Likely, or Possible) reflecting how often the queries occurred, how recent they are, and how unlike any existing topic they are.
For each suggestion you can:
Dismiss (the X): remove a suggestion that is off-topic or already covered.
Create topic (the +): create a draft topic seeded with the suggested title and open it in the editor. The gap is marked as addressed.
Triage strongest-confidence gaps first. A Strong gap means several recent readers asked something your docs do not cover at all, the clearest signal to write a new topic.
Searches with no answer
The Searches with no answer section lists the reader AI questions that returned nothing, unclustered: the unprocessed demand signal. Each row shows the query, how many times it was asked, and when it was last asked. Choose Create topic to start a draft with the query as its working title.
Not every gap needs a new topic. Some queries are off-topic or outside your documentation's scope, and some are better answered by improving an existing topic than by adding a new one. Use the suggested title and query count as guidance, not a mandate.
Where gaps come from
Gap detection runs automatically each week for eligible projects, over the last 30 days of reader activity on your published targets. It reads two streams: AI questions that returned no more than one result or drew a thumbs-down, and keyword searches that returned nothing. Questions where the AI itself failed, through an error or a cut-off answer, are excluded, so an outage never invents demand. A cluster needs at least 3 queries before it becomes a suggestion, so single one-off questions do not create noise.
Act on gaps from the worklist
Every suggested gap also enters the Prioritize what to write next worklist as a Reader gap item, ranked against health-scan findings, code changes, and failing docs tests. There, the primary action is Create draft, and the queries behind the gap open from a link on the row labelled with their count, for example 11 reader queries.
Use this tab to triage gaps on their own. Use Demand to decide whether a gap outranks the other work waiting.
See also
Prioritize what to write next: gaps and content-health signals ranked into one worklist
AI queries and crawler activity: what readers ask the on-site AI
Monitor search analytics: keyword search gaps from the search widget
Improve AI search readiness (GEO): make existing pages easier for AI engines to fetch, parse, and answer from