Lane Planner
Optimize auction lanes by D/S ratios — maximize sell-through with data-driven segment and model selection
Purpose
Lane composition is one of the highest-leverage decisions an auction manager makes — and it is routinely based on what came in rather than what will sell. A lane full of sedans in a pickup-dominant market will hit 60% sell-through while a competitor running the same event with the right segment mix hits 90%. The difference in fee revenue on a 100-unit sale at average hammer of $25,000 is $112,500.
Lane Planner calculates demand-to-supply ratios for every vehicle segment in the target DMA, identifies HOT (D/S > 2.0), WARM (D/S 1.0–2.0), COOL (D/S 0.5–1.0), and DECLINING segments, predicts sell-through % per segment, estimates fee revenue per unit, and allocates lane slots proportionally — then identifies the three fastest-turning specific models to source and any segments to reduce.
How It Works
Execution flow. MCP tool calls are shown inline on each step.
get_sold_summaryCalls get_sold_summary by body_type for the state, current month, with ranking_measure=sold_count. Extracts sold_count, average_sale_price, and average_days_on_market per segment.
get_sold_summarySame call shifted back one month to calculate volume trend per segment.
get_sold_summaryCalls get_sold_summary by make,model ranked by average_days_on_market ascending for the state to identify the 20 fastest-turning models.
search_active_carsCalls search_active_cars for the state with body_type facets and DOM stats to get active supply per segment and median price.
Per segment: D/S Ratio = monthly_sold / active_supply. Volume Trend = MoM%. Predicted sell-through = 90–95% (D/S > 2.0), 75–90% (1.0–2.0), 60–75% (0.5–1.0), 40–60% (< 0.5). Expected hammer = avg_sale_price × 0.88. Revenue per unit = expected_hammer × (buyer_fee + seller_fee) / 100.
If avg_weekly_lanes is known: HOT segments get 40%, WARM 35%, COOL 15%, specialty 10%. If unknown, provides proportional recommendations only.
MCP Tool Calls
| Tool | Calls | Purpose |
|---|---|---|
get_sold_summary | 3 | Segment demand current + prior, fastest-turning models |
search_active_cars | 1 | Current supply by segment for D/S calculation |
Example Output
LANE PLANNER — Texas | Next Sale (March 19, 2026) Profile: 8 lanes per sale | Target sell-through: 85% ════════════════════════════════════════════════════ LANE ALLOCATION RECOMMENDATIONS Segment D/S Ratio Sell-Through% Avg Hammer Fee/Unit Signal Trend Lanes ──────── ───────── ───────────── ────────── ──────── ────────── ───── ───── Pickup 2.07 90–95% $33,600 $2,688 HOT ● ↑ 3 SUV 1.98 85–90% $28,400 $2,272 HOT ● ↑ 3 Sedan 1.74 80–85% $19,600 $1,568 WARM ◐ → 1 Luxury 1.48 75–80% $42,100 $3,368 WARM ◐ ↓ 0.5 Minivan 0.79 60–65% $16,800 $1,344 COOL ○ ↓ 0.5 EV 1.27 70–75% $31,200 $2,496 WARM ◐ ↑ (specialty) Total recommended: 8 lanes Predicted overall sell-through: 87.3% (above 85% target ✓) EVENT REVENUE FORECAST Recommended units: 72 (8 lanes × 9 avg units) Predicted sell count: 63 vehicles (87.3%) Predicted gross hammer: $1,782,000 Predicted total fees: $142,560 TOP MODELS TO SOURCE (fastest turning in Texas) 1. Toyota Tacoma TRD — 16-day avg DOM, D/S 2.31 — source aggressively 2. Toyota RAV4 XSE — 18-day avg DOM, D/S 2.08 — strong buyer demand 3. Ford F-150 XLT — 22-day avg DOM, D/S 1.94 — reliable seller REDUCE: Minivan lanes to 0.5 — soft demand (D/S 0.79), risk of no-sales SOURCE MORE: Pickup and SUV — these are the profit-driving segments
Cost Estimate
8 lane plans/month ≈ $1–3
Limitations
- US (full) and UK (search_uk_active_cars supply only — no demand data; sell-through prediction not available for UK).
- Lane allocation requires avg_weekly_lanes from profile — if unknown, skill provides proportional recommendations only.
- Sell-through prediction is a statistical estimate based on D/S ratios — actual results depend on bidder attendance, reserve pricing, and run list quality.
- Model-level lane planning multiplies API calls proportionally for supply checks per model.