Import runs
Every import extracts facts with provenance, proposes changes, and waits for review. Nothing writes to the catalog without an approval trail — except unambiguous updates, which auto-apply and stay auditable.
Brown Jordan 2026 Price List Update
Brown Jordan · Jul 3, 2026 · sources: BJ_2026_PriceList_v2.xlsx, BJ_2026_Catalog.pdf, brownjordan.com product pages
214
facts
41
auto-applied
7
pending
1
conflicts
Pacific Green 2026 Catalog + Pricing Payload
Pacific Green · May 12, 2026 · sources: PG_2026_pricing_payload.xlsx
96
facts
12
auto-applied
0
pending
0
conflicts
Brown Jordan 2025 Initial Import
Brown Jordan · Nov 2, 2025
480
facts
55
auto-applied
0
pending
4
conflicts
How a run works
- Extract — parsers pull atomic facts (price, header, suffix, option mention) from each source with a locator and a confidence score.
- Compare — facts are diffed against the current catalog and against each other; agreeing sources raise confidence, disagreeing sources create conflicts.
- Propose — changes become proposals (price update, new item, discontinue, new rule, new resolver). Unambiguous ones (single source, matches expectations, high confidence) auto-apply.
- Review — everything else waits in the run's proposal list or the review queue, with a preview of exactly which items change and how.
- Watch — applied changes that affect finalized/sent quotes flag those quotes for attention; the frozen documents never mutate.