Signal

Query-conditional rewrites are a targeted experiment

Rewriting descriptions to match likely queries produces concentrated, not universal, gains, so treat it as a measured experiment on candidate SKUs rather than a blanket promise.

AffectsComparisonEvidenceReportedConfidenceHighImpact2/3Last verified2026-07-08

Per-platform status

Where a platform documents relevant behavior, its status and source are shown. Undocumented platforms show "unknown" - honest unknowns, never invented.

Platform	Status	Notes	Source
ChatGPT	Unknown	Not documented by this platform.	-
Gemini / Google AI Mode	Unknown	Not documented by this platform.	-
Perplexity	Unknown	Not documented by this platform.	-
Copilot	Unknown	Not documented by this platform.	-
Claude	Unknown	Not documented by this platform.	-

Evidence and sources

This signal is typed reported (High confidence).

ACES (arXiv:2508.02630) (opens in new tab) · 2026-07-08

How to act on this

Rewrite a small batch of candidate SKUs (same facts, no new claims), measure win rate per engine before and after, and serve identical copy to bots and humans.

Related checklist items

Test query-conditional description rewrites where they plausibly help, expecting concentrated, not universal, gains. Selection

Handbook chapters

Information Density: Facts Per Token on Machine Surfaces

Related signals

Notes

Based on ACES (arXiv:2508.02630), a controlled agent-shopping simulation, not measured real-world sales.