GeoCheckTool Research

Original measurements for the parts of AI search dashboards cannot explain.

We publish the frozen questions, raw measurement boundaries, confounds, coding decisions, and open data behind each technical note. A result stays an observation until the evidence supports something stronger.

Open datasetsFrozen methodsExplicit limitations

Featured · Published July 30, 2026

Flagship report

R1 · State of AI Search in China

The State of AI Search in China: We classified every citation behind China's biggest AI assistant's brand advice. Then we found the price list.

A citation-by-citation audit of China's biggest AI assistant: 641 classified citations, a public placement price list, a failed causal test, and the evidence boundaries brands need to understand.

Read the flagship report

Published

Industry and technical notes

Every note preserves its question scope, collection layer, sample size, verification limits, and failed observations.

Industry Note · R2b-2Published August 4, 2026

The empty shelf: maternity, supplements, pet food on China's biggest AI assistant

The finding this time is an absence: in dietary supplements, 61.4% of answers named no identifiable candidate at all. The shelf is largely empty — and one of the names that keeps appearing is the regulator.

Read industry note R2b-2

Industry Note · R2bPublished July 30, 2026

Who China's biggest AI assistant actually names: beauty, luxury, cars

A 210-question API snapshot showing how beauty answers favor SKUs, luxury answers favor authentication infrastructure, and car answers mix platforms, models, and brands.

Read the industry note

Technical Note 01Published July 28, 2026

Same Question, Same Engine, Two Devices: Retrieval Asymmetry in China's Biggest AI Assistant

We ran 30 frozen questions on both the web version and the mobile app of Doubao, China's most-used AI assistant. Web displayed more sources in 14 of 16 valid pairs; mobile never exceeded it. Full dataset, question bank and confounds published under CC BY 4.0.

Read the note

Measurement program

Next in the series

TN-02 · Planned

Query expansion

What the engine silently turns a question into before retrieval.

TN-03 · Planned

Source adoption

When a retrieved page informs the answer—and when it does not.

TN-04 · Planned

Entity boundaries

How adjacent companies, credentials, products, and capabilities merge.

TN-05 · Planned

Claim escalation

Commercial claims that become stronger than their cited sources.

TN-06 · Planned

Recommendation sets

How candidate lists widen, contract, and change across surfaces.

TN-07 · Planned

Retest stability

What repeats when the question, entity, method, and window stay frozen.

Want this run on your brand? China Evidence Snapshot — $390