AI audit vs rubric — Doba
An independent Workers AI LLM scored Doba 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 | 75 | 0 | -75 |
| Product range | 85 | 55 | -30 |
| Access & onboarding | 65 | 40 | -25 |
| Support track record | 72 | 0 | -72 |
| Store integrations | 85 | 40 | -45 |
| Overall | 71 | 34 | -37 |
What this means: Large disagreement — investigate. The LLM read the published signals very differently from the deterministic rules.
Median per-dimension |Δ| = 37.5.
Doba's pricing is opaque, requiring signup to view product prices. Business transparency is limited, with no publicly listed company and no audited statements. Shipping information is generic, and review scores are missing. The product range is estimated at 2M+ SKUs, but access is restricted to a paid plan with signup required to browse. Support feedback is consistently poor, and integration is limited to 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.