Not sure where to start? Take a guided tour.
AI Site Grader
AI Query Scanner
llms.txt GeneratorAI injects current-year terms in about one quarter of searches
AI added a year term in 25.66% of observed query rewrites.
An analysis of 11,521 prompt-to-query transformations revealed that artificial intelligence systems injected a current-year term into 2,956 queries during the rewrite process.
The numbers behind it.
- Year injection rate
- 2,956 queries injected a year term.
- 25.66%
- Prompt-query pairs
- Captured prompt-to-query transformations.
- 11,521
The evidence.
| Measure | Result |
|---|---|
| Year injection rate 2,956 queries injected a year term. | 25.66% |
| Prompt-query pairs Captured prompt-to-query transformations. | 11,521 |
Population and method
Built from 11,521 captured prompt-to-query pairs observed in OpenAI web search calls, with 100% search-query coverage in the sampled dataset.
Where the evidence stops
This study reflects captured search-query transformations rather than every hidden retrieval step a model may perform.
Some inserted entities reflect category heuristics or market leaders rather than final recommendation outcomes.
The underlying dataset is concentrated in commercial and research prompts rather than all possible conversational traffic.
What to do with this
Current-year framing operates as a primary retrieval signal before functioning as a ranking or citation signal. Strategists must ensure content is explicitly dated to align with automated temporal query expansions.
Cite this fact.
Source study: Query Translation“AI added a year term in 25.66% of observed query rewrites.”
How AI Translates Your Questions - Trakkr Research · AI injects current-year terms in about one quarter of searches
How AI Translates Your Questions · Trakkr Research · Updated 22 January 2026