Date anchor: Today's date comes from the # currentDate system context. Compute ALL relative dates from it. Example: if today = 2026-03-14, then "prior month" = 2026-02-01 to 2026-02-28, "current month" (most recent complete) = February 2026, "three months ago" = December 2025. Never use training-data dates.

Lending Fit Analyzer — Overlay Lending Criteria on a Dealer's Lot

Profile

Load the marketcheck-profile.md project memory file if exists. Extract: price_range_min, price_range_max, preferred_year_range, max_mileage, approved_makes, approved_segments, ltv_max_pct, country, zip, radius. If missing, ask minimum fields. US: search_active_cars, predict_price_with_comparables. UK: search_uk_active_cars only (no LTV check — skip predict calls). Confirm: "Using profile: [company], [lending_type]". All preference values from profile — do not re-ask.

User Context

Lender sales rep wants to precisely quantify how much of a dealer's lot they can finance. Used to prepare proposals, justify partnerships, and identify gap opportunities.

Gotchas

1. LTV direction matters. LTV = listed_price / predicted_price x 100. Values OVER 100% mean the dealer is listing above market value (higher lender risk). Values UNDER 100% mean the dealer is listing below market (lower risk, easier to advance on). Do not invert this ratio.
2. UK profiles — no LTV analysis. predict_price_with_comparables is US-only. For UK dealers, skip step 3 (LTV analysis) entirely and present coverage % only. Note "LTV analysis unavailable for UK market" in the output.
3. Sampling bias in LTV spot-check. The 10-unit sample (3 cheapest, 4 median, 3 most expensive) is designed to capture the range, but may miss outliers. Always note the sample size and that LTV estimates are based on a representative sample, not a full-lot appraisal.
4. Make/segment filters are AND conditions. If both approved_makes and approved_segments are set, the search requires BOTH to match. This can dramatically reduce the matching count. Report the filter combination used so the user understands why coverage might be low.
5. Gap analysis should be actionable. Saying "200 units are outside price range" is less useful than "expanding your price ceiling from $55K to $65K would add 45 units (12% coverage gain)." Always quantify what loosening one constraint would yield.

Workflow: Full Fit Analysis