See which content signals are getting cited by AI engines for each of your monitored prompts — and compare your own pages against the patterns.
Last updated
Ultra & Enterprise only. Citation Patterns is a multimodal analysis layer that runs on top of prompt monitoring. It tells you why the AI engines cited the sources they did — and what's different about your own content.
Every time the prompt-monitor scrapes a prompt across the 8 AI engines (ChatGPT, Perplexity, Gemini, Claude, Grok, Copilot, Google AI Overviews, Google AI Mode), the Citation Pattern agent picks up where the scrape leaves off:
In Prompt Monitoring, click the ✨ sparkle icon next to any prompt's citation count. A modal opens with the latest snapshot.
A horizontal bar chart of the signals that appear across the cited sources for this prompt. Red bars are gaps where the signal is frequent but your content lacks it. Green bars are signals you already have.
Signals come from a closed, curated vocabulary that includes:
A small heatmap showing which signals each engine tends to favour for this specific prompt. ChatGPT might lean on editorial authority while Perplexity prefers original statistics. Use this to pick which signal to chase per engine.
A ranked list of signals where your content trails the cited sources. Each gap has a severity badge (high / medium / low), an indicator showing whether competitors have it, and a one-line recommendation.
3–5 short, opinionated actions. Each one links to exemplar URLs from the cited sources so you can see what "good" looks like.
The most-cited domains across this prompt's responses, with each domain's source type (UGC / Editorial / Corporate / Competitor / Other) and a media-type hint icon.
The default brand baseline is automatic — it uses your GEO audit if available, otherwise it samples a few of your top pages. But for the highest-quality recommendations, you should tell the agent exactly which of your assets to compare against the cited sources.
In the modal, look for the "Not seeing precise gaps?" form. Paste 1–5 HTTPS URLs of your matching content (a product page, a whitepaper, a blog post — whatever you think should be getting cited for this prompt). Click Recalculate.
The agent will:
This converts Citation Patterns from a passive dashboard into an interactive content workbook.
Citation Patterns aggregates automatically after every monitored-prompt scrape, provided at least 2 of the 8 AI engines returned usable responses. Snapshots are idempotent by UTC date — running twice on the same day overwrites the morning's snapshot rather than duplicating it.
On-demand recalculates via the asset-override form bypass the daily cadence — they invoke the agent synchronously and produce a fresh snapshot in seconds.
file_data.file_uri — Gemini processes audio + visual at 1 fps + 1 Kbps directly, no transcript scraping)All cited-source feature extraction is cached globally across the customer base (one fetch + extraction per URL per week, no matter how many tenants cite it), while the per-tenant reasoning is computed against your specific responses and brand context.
Ultra & Enterprise. Being switched on in stages: if you do not see the What the pages say tab in the pop-up yet, it is not on for your workspace.
Citation Patterns tells you which signals the cited pages share. What the pages say tells you what they are about, and what to write.
Open the pop-up from a question on the Prompts page and choose the What the pages say tab. Press Analyse cited pages (the price in credits is on the button; the credits are only taken if the analysis finishes). It takes about two to three minutes, and you get a notice in the bell when it is ready. For one question it:
What you see:
You can also ask Vizzy: "What should I write to get cited for <your question>?" Vizzy reads the latest analysis, and offers to run one (with its price) if there is none.
A question analysed less than 7 days ago, with no new answers since, shows that analysis instead of offering a new one. One analysis runs at a time per workspace.