AI audit vs rubric — Spocket
An independent Workers AI LLM scored Spocket 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 | 86 | 0 | -86 |
| Product range | 85 | 70 | -15 |
| Access & onboarding | 65 | 40 | -25 |
| Support track record | 82 | 65 | -17 |
| Store integrations | 85 | 60 | -25 |
| Overall | 76 | 47 | -29 |
What this means: Large disagreement — investigate. The LLM read the published signals very differently from the deterministic rules.
Median per-dimension |Δ| = 21.
Spocket's pricing is opaque, business information is limited, and review score is unavailable. However, shipping clarity is high, product range is large, access is moderately restricted, support is mostly positive, and integration is somewhat limited.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.