AI audit vs rubric — AutoDS

An independent Workers AI LLM scored AutoDS against the same published rubric. The deterministic rubric result is our canonical score. The LLM's result is shown here as a sanity check — never mixed into the scoring formula.

Dimension Rubric LLM Δ (LLM − Rubric)
Pricing transparency 84 20 -64
Business transparency 40 25 -15
Shipping clarity 92 85 -7
Public reviews 82 0 -82
Product range 95 70 -25
Access & onboarding 65 40 -25
Support track record 78 65 -13
Store integrations 95 75 -20
Overall 77 44 -33
What this means: Large disagreement — investigate. The LLM read the published signals very differently from the deterministic rules. Median per-dimension |Δ| = 22.5.
Low pricing transparency due to no source price visible. Business transparency is low as the company is not publicly listed. Review score is 0 due to no reviews. Product range is mid due to 100K+ SKUs. Access is low due to paid only with demo. Support is mid due to mostly positive feedback. Integration is high due to native across 4-5 platforms.
This is the LLM's own explanation, not editorial commentary from SupplierSpy. The LLM result is a sanity check on the rubric — never mixed into the scoring formula.