- Reviewer decision loop: approve / reject (default Tier 2) / more evidence; decisions recorded in VALIDATION.md
- Blocked surfaces: customer-facing block = finding or documented limitation, never a bare marker
- Pre-delivery consistency gate: count match, evidence present, identity match
- Required artifact set per run; deviations require dated decision record
- Gilmore: exec summary corrected 2->3 to match findings; VALIDATION.md added with reviewer dispositions
- Reviewer decision loop: approve / reject (default Tier 2) / more evidence; decisions recorded in VALIDATION.md
- Blocked surfaces: customer-facing block = finding or documented limitation, never a bare marker
- Pre-delivery consistency gate: count match, evidence present, identity match
- Required artifact set per run; deviations require dated decision record
- Gilmore: exec summary corrected 2->3 to match findings; VALIDATION.md added with reviewer dispositions
Internal proof run on Phoenix Salon + Spa (Cameron Park, CA) using the new
pipeline. 4 surfaces captured (GBP 4.9/64, Apple 4.9/65, Bing 5.0/65,
website). After engine normalization the report is a clean 2-finding set:
hours mismatch (Immediate) + stale reviews 115d (High). Address/category
false positives removed. Serves as the 'after' baseline for a future
before/after comparison.
Raw multi-surface JSON, engine findings (json+md), and VALIDATION.md for the
Superior HVAC & Plumbing (Cameron Park) run. All 4 surfaces returned data;
the pipeline correctly captured genuine cross-source NAP divergence (3
different business names, 2.7 vs 4.5 vs null ratings, conflicting phones and
hours) as evidence rather than error. GBP phone glyph-stripped to
'(909) 319-0746'.
Raw multi-surface JSON, engine findings (json+md), and VALIDATION.md for the
Crystal Blue Plumbing Heating & Air run. Demonstrates the GBP match gate
rejecting a wrong entity and falling back to Apple with a glyph-clean phone
('+1 (916) 571-6448').