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.

get_sold_summary parameter safety:

• Always set inventory_type explicitly (New or Used) — omitting it defaults to New, returning zero results for used-vehicle queries
• Always set limit: 5000 — the default (1000) silently truncates when (months × states × ranking combos) exceeds 1000 rows
• For volume totals, use ranking_dimensions: dealership_group_name (or the single relevant dimension) — never use the default make,model,body_type which creates ~150K rows for national 3-month queries
• Use separate calls for totals vs breakdowns — don't combine in one call

EV Lending Risk Monitor — EV Intelligence for Lender Sales Reps

Profile

Load the marketcheck-profile.md project memory file if exists. Extract: target_states, country. If missing, ask for state. US only — requires get_sold_summary. Confirm: "Using profile: [company], [lending_type], [state]".

User Context

Lender sales rep needs to understand EV market dynamics to: (1) advise dealers on which EV lending programs to promote, (2) identify which EV models are safe to lend on (strong residuals), and (3) flag high-risk EV segments. This is sales enablement, not portfolio risk management.

Gotchas