POS Sales Velocity Analyzer

What it does

POS Sales Velocity Analyzer connects to Square POS to pull the last 30 days of item-level sales data and applies the Menu Engineering matrix (Stars, Plow Horses, Puzzles, Dogs) based on each item's sales velocity (units/day) and contribution margin. It returns prioritized discount, promotion, or removal recommendations for underperforming menu items, with an optional Google Sheets export. Falls back to deterministic mock fixtures when no Square credentials are configured. Decision-support only — menu changes are drafted, never auto-applied. Built for restaurant, cafe, and food-and-beverage operators who want a data-driven menu review instead of manually reconciling POS reports.

Example prompts

• Run the full Menu Engineering analysis on our Square POS data
• Which menu items are dogs and should be removed or reworked?
• Classify this menu item given its sales velocity and margin
• Get top recommendations for our puzzle items

Tools (7)

Tools the agent exposes — your AI client calls them automatically when it needs them.

• run_full — Run the POS Sales Velocity Analyzer end-to-end: collect Square POS data, apply the Menu Engineering matrix, synthesize an LLM narrative, return the full AgentResult JSON.
• analyze_menu — Given a raw menu dataset, run the deterministic Menu Engineering matrix (no LLM) and return classified items, recommendations, and findings.
• get_recommendations — Get prioritized menu recommendations filtered by ME category (dogs, puzzles, plow_horses, stars, or all).
• classify_item — Classify a single menu item into the Menu Engineering quadrant given its sales stats.
• list_capabilities — List the agent's static capabilities: available tools, ME categories, and credential slots.
• plan_inputs — Plan inputs for a tool: returns questions, schema, and a ready-to-edit example.
• discover_intent — Proactive intent discovery: restate the goal, ask clarifying questions, propose a concrete input.