AI audit vs rubric — DSers
An independent Workers AI LLM scored DSers 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 | 70 | 40 | -30 |
| Public reviews | 92 | 60 | -32 |
| Product range | 95 | 70 | -25 |
| Access & onboarding | 95 | 90 | -5 |
| Support track record | 82 | 65 | -17 |
| Store integrations | 85 | 60 | -25 |
| Overall | 79 | 51 | -28 |
What this means: Large disagreement — investigate. The LLM read the published signals very differently from the deterministic rules.
Median per-dimension |Δ| = 25.
Pricing transparency is low because pricing is not visible without signup. Business transparency is low because the company is not publicly listed and audited statements are not available. Shipping clarity is low because origins and delivery windows are not clearly published per region. Review score is moderate because the weighted average of public review sources is 4.0-4.3 stars. Product range is moderate because the catalog size is 100K+ SKUs. Access is high because a free plan is available with no signup required to browse. Support is moderate because customer-support reputation is mostly positive with few complaints. Integration is moderate because native integrations are available with 2-3 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.