AI Search Metric
Source recency
How recent the sources cited in an AI answer are. Recency-weighted models favour fresh content; signals when an LLM is treating a topic as time-sensitive.
What it is
Source recency measures how recent the sources cited in an AI answer are, from publication or last-updated dates. It indicates whether a model is favouring fresh material for a given topic.
Why it matters
Recency-weighted models favour fresh content, so this metric signals when an LLM treats a topic as time-sensitive and rewards updates, which tells you where freshness drives visibility.
How it works
Practitioners record the age of cited sources across a prompt set and look for topics where recent dates dominate, then maintain a refresh cadence on content in those time-sensitive areas.
When it applies
Act on it for topics where answers consistently cite recent sources, signalling that freshness matters.
Examples
- A topic where cited sources are mostly weeks old rather than years
- A brand refreshing a guide and regaining citations on a fast-moving subject
- A team spotting that evergreen topics tolerate older sources while news-like ones do not
How it is measured
- Median age of cited sources per prompt
- Share of citations published within a recent window
- Recency distribution compared across topics
- Change in citations after a content refresh
Related terms in AI Search Metric
- AI-referred trafficSessions referred from ChatGPT, Claude, Gemini, Perplexity, Copilot, and other LLM surfaces. Often under-counted in standard analytics because referrers are stripped or labelled as direct.
- Answer attribution rateThe proportion of AI answers that explicitly link back to source pages versus those that summarise without attribution. Attribution rate varies materially by platform and query type.
- Bounce-back rate (AI surface)The rate at which users return to the SERP or refine the prompt after seeing an AI Overview. Google's internal signal that an Overview failed, high bounce-back is associated with Overviews being silently removed for that query cluster.
- Brand mention rateThe frequency at which an LLM mentions a brand by name in answers across a prompt set, with or without citation. Brand mentions without citation are an early indicator of model-internalised brand awareness.
- Citation depthHow early in an AI-generated answer a source is cited. Earlier citations correlate with higher click-through from AI surfaces and stronger user trust signals.
- Citation diversity indexThe number of distinct domains an LLM cites across a prompt set, normalised by prompt count. Falling diversity in a category signals consolidation, and a closing window for new entrants.