recentcomp
Citation-anchored valuation reports for luxury-asset lenders. Next.js app plus a comp-discovery engine spanning nine auction, dealer and marketplace sources, piloted with Luxury Asset Capital.
Where it stands
Lenders against luxury assets need defensible valuations fast. Comparable sales are scattered across auction archives, dealers and marketplaces, and most tooling produces numbers without receipts. recentcomp generates reports where every figure traces to a cited, timestamped comparable sale.
Luxury Asset Capital (LAC) is the pilot customer — loan officers and valuation analysts underwriting watches, handbags and cars. Built to generalize to other lending desks after the pilot.
LAC underwrites on recentcomp: reports move draft to approved inside the product, the team's verified-comp history compounds with use, and every valuation survives scrutiny — audit ledger, per-figure citations, 90-day reproducibility.
Cars & Bids and Fashionphile/Rebag adapters
LAC's top-ranked missing sources for cars and handbags (engine #22, #21)
Latest updates
Driven by a review of LAC report history since September (8 of 31 reports failed, 16 stalled at review). Valuations now use realized sales only, with a reference check that withholds the loan when comps name a different watch. Intake sets category from photos; the review step shows a suggested value; reports can be re-run in place; analysts can flag issues on any report. The engine gained Doyle, Freemans | Hindman, Rago, LA Modern, Chrono24, 1stDibs, Vestiaire, Classic.com, CarFax and AutoTempest, keyword search across the auction houses, and jewelry, fine art, clothing and miscellaneous categories. Open: Tavily quota exhausted, gold spot-price source, Heritage account.
Rich reviewed the new features live. Photo identification impressed; three gaps drove immediate work. Shipped same day: a review-then-generate step (candidates surfaced for selection before any valuation exists), adjust-search-and-rerun on the same report, visible sort affordances on every column, and a query-hash fix. Filed to the engine: stricter watch matching (a 16610 search surfaced 16610LV Kermits and modern larger cases, issue 59), run-to-run consistency (photo-keyed caching defeats cache hits across reports, issue 60), and the requested WatchCharts market-value benchmark (issue 61, gated on API access).
Replayed all 15 August inputs with the original reference photos re-attached, against the engine after its #33 to #38 fixes plus query normalization on the recentcomp side. Hermès Kelly 32: 0 to 22 comps. Louboutin Cabata Mini: 0 to 19 comps, 3 realized. Pochette Accessoires: 18 to 37 comps with 14 realized TheRealReal sales. Rolex 126603: 5 to 26 comps, 7 exact photo matches. Rolex 116000: 2 to 176 realized sales. The two brand-only searches, one of which produced the 134-Rolex, $52,559 report, are now refused at intake. Still open: Chrome Hearts ring finds nothing (jewelry is not a category yet), and handbag photo tiers came back all variant with no exact matches on three runs, raised with the engine. The comp table now sinks unjudged comps and orders exact photo matches ahead of variants, with the engine note shown.