--- name: pangzhenying2025/automotive-aftermarket source: https://app.decimal.ai/s/pangzhenying2025-automotive-aftermarket@1/SKILL.md source_sha256: b556ac1ea00b --- # Automotive Retail Aftermarket 25 skill files covering retail-aftermarket domain for automotive software engineering. ## Applicable Standards - ACES (Aftermarket catalog exchange standard) - ACES/PIES (Aftermarket catalog and parts interchange) - ASAM OpenSCENARIO (Scenario-based simulation standards) - ASE technician certification for mobile service - AUTOSAR Adaptive Platform (Service-oriented architecture) - CARFAX/AutoCheck standard data interchange formats - CCPA (California consumer privacy for automotive data) - DVIR (Driver Vehicle Inspection Report requirements) - ECE R21 (Interior fittings safety requirements) - EDIFACT/EDI (Electronic data interchange for B2B orders) - ELD mandate (Electronic Logging Device for HOS compliance) - EPA regulations for mobile fluid handling and disposal - EU Block Exemption Regulation (BER) for motor vehicle distribution - EU Directive 2019/771 (Consumer goods guarantee) - EU Regulation 2018/858 (Vehicle type approval and records) - FMI 2.0 (Functional Mock-up Interface for model exchange) - FMVSS 201 (Occupant protection in interior impact) - FTC Franchise Rule and state dealership laws - FTC Franchise Rule compliance for agency transitions - FTC guidelines for loyalty program transparency - GDPR (Avatar identity and behavioral data privacy) - GDPR (Customer data ownership in agency model) - GDPR (Customer data privacy and consent management) - GDPR / CCPA (Customer privacy in direct sales channels) - GDPR / CCPA (Loyalty program data privacy) - GDPR / CCPA (Subscriber data privacy and consent) - GDPR / CCPA (Telematics data privacy and consent) - GS1 GTIN (Global trade item number for parts identification) - GS1 standards (Parts barcoding and identification) - GS1 standards (Parts identification and traceability) - IATF 16949 (Quality management for AM in automotive) - IATF 16949 (Quality management in automotive supply chain) - IFTA (International Fuel Tax Agreement reporting) - ISO 11452 (EMC requirements for electronic accessories) - ISO 14229 (Unified Diagnostic Services - UDS) - ISO 15031 (OBD-II communication standards) - ISO 20022 (Financial messaging for warranty transactions) - ISO 20078 (Extended vehicle access and data) - ISO 20078 (Extended vehicle web services for data access) - ISO 20078 (Extended vehicle web services) - ISO 21434 (Cybersecurity for feature activation systems) - ISO 21434 (Cybersecurity for software update channels) - ISO 23247 (Digital twin framework for manufacturing) - ISO 24089 (Software update engineering for road vehicles) - ISO 24089 (Software update engineering) - ISO 26262 (Functional safety for OTA software changes) - ISO 26262 (Functional safety for software-activated features) - ISO 26262 (Safety for software-defined vehicle functions) - ISO 26262 (Safety validation of simulated vehicle behavior) - ISO 27001 (Customer and vehicle data security) - ISO 27001 (Customer data protection in digital retail) - ISO 27001 (Customer data security in D2C platforms) - ISO 27001 (Customer financial data protection) - ISO 27001 (Customer vehicle data protection) - ISO 27001 (Data governance in shared OEM-dealer systems) - ISO 27001 (Data security in metaverse transactions) - ISO 27001 (Fleet data security and multi-tenant isolation) - ISO 27001 (Information security for customer data) - ISO 27001 (Loyalty platform data security) - ISO 27001 (Service record data security) - ISO 27001 (Warranty data security) - ISO 27701 (Privacy information management) - ISO 28000 (Supply chain security management) - ISO 45001 (Occupational health and safety for field work) - ISO 55000 (Asset management for parts inventory) - ISO 9001 (Quality management for logistics operations) - ISO/ASTM 52900 (Additive manufacturing terminology) - ISO/ASTM 52920 (AM qualification principles) - Kelley Blue Book and NADA valuation methodologies - MMOG/LE (Materials management operations guideline) - Magnuson-Moss Warranty Act (US warranty requirements) - NAAA condition grading standards for vehicle assessment - NAIC Usage-Based Insurance Model Act - OSHA mobile workshop safety requirements - OpenXR 1.0 (Cross-platform VR/AR runtime standard) - PCI DSS (Payment and rewards card processing) - PCI DSS (Payment card security for online transactions) - PCI DSS (Payment processing for direct vehicle sales) - PCI DSS (Recurring payment processing compliance) - PIES (Product information exchange standard) - PSD2 (Payment services for microtransactions) - SAE J1739 (FMEA for accessory design risk assessment) - SAE J1979 (OBD-II diagnostic test modes) - SAE J2464 (Vehicle condition assessment standards) - SAE J3061 (Connected vehicle cybersecurity for shared assets) - SAE J3061 (Cybersecurity for connected shared vehicles) - SAE J3061 (Cybersecurity for telematics data transmission) - TecDoc (European parts catalog data standard) - UNECE WP.29 R156 (Software update management system) - VDA 6.3 (Process audit for additive manufacturing) - WCAG 2.1 (Accessibility for ecommerce platforms) - WCAG 2.1 AA (Accessibility for virtual showroom interfaces) - WebXR Device API (W3C immersive web standard) - WebXR Device API (W3C standard for immersive web experiences) - glTF 2.0 (3D model interchange for vehicle assets) ## Use Cases - Online accessory configurator with 3D visualization - Custom interior trim design with material preview - Personalized exterior styling packages - 3D-printed custom accessories ordered online - Dealer-installed accessory recommendation engine - OEM transition from franchise to agency distribution - Fixed-price retail with dealer commission structures - Centralized inventory and pricing management - Dealer network transformation and change management - Hybrid agency models combining online and physical touchpoints - AI-optimized route planning for parts delivery fleets - Warehouse robot orchestration for parts picking - Same-day and next-day parts delivery to workshops - Predictive pre-positioning of fast-moving parts - Drone and autonomous vehicle last-mile delivery pilots - Multi-vendor parts marketplace for workshop procurement - Supplier onboarding and qualification platform - Real-time inventory visibility across distributor network - Dynamic pricing and automated RFQ processing - Cross-border parts sourcing with compliance automation ## Topics Covered ### Analytics - customer-data-platform ### Customer Engagement - loyalty-program-automotive ### Customization - accessory-personalization - three-d-printed-parts ### Digital Commerce - ecommerce-integration ### Digital Retail - digital-twin-sales - metaverse-dealership - virtual-showroom ### Fleet Services - fleet-management-saas ### Insurance Finance - usage-based-insurance ### Monetization - feature-on-demand - software-as-feature ### Ownership Models - subscription-ownership - vehicle-as-a-service ### Parts Supply - automated-logistics - b2b-parts-marketplace - predictive-aftermarket ### Sales Channels - agency-model - direct-to-consumer ### Service Operations - mobile-service-vans - ota-repair - remote-diagnostics-retail ### Valuation - remote-vehicle-appraisal ### Warranty Service - blockchain-service-records - digital-warranty ## Constraints - 3D printed parts must use automotive-grade materials - 99.95% platform uptime SLA - Accessible UI for non-technical automotive buyers - All accessories must pass OEM fitment validation - Appraisal generation within 60 seconds of photo submission - Automatic rollback within 120 seconds on installation failure - Blockchain transaction finality under 30 seconds - Catalog must handle 5M+ part numbers with fitment data - Claim verification response under 5 seconds - Critical fault notification within 60 seconds - Custom order fulfillment within 10 business days - Customer experience quality cannot degrade during transition - Damage detection accuracy above 85% versus expert assessment - Dealer profitability must remain viable post-transition - Diagnostic accuracy above 85% versus workshop verification ## Required Tools - 3DPrinterOS or 3YOURMIND for print farm management - 8th Wall or WebXR for AR experiences - AUTOSAR Adaptive Platform for service-oriented base - AWS IoT Core or Azure IoT Hub for device connectivity - AWS IoT Core or Azure IoT Hub for vehicle connectivity - AWS IoT or Azure IoT for vehicle fleet management - AWS or GCP for cloud infrastructure - Akeneo or Salsify for product information management - Apache Airflow for pipeline orchestration - Apache Kafka for diagnostic event streaming - Apache Kafka for real-time event streaming - Apache Kafka for telematics data streaming - Blender for accessory 3D model creation - Blender or 3ds Max for asset preparation - Continental or Bosch digital key SDK ## Instructions ### accessory-personalization ## Core Competencies You are an expert in automotive accessory personalization with deep knowledge of: - Digital accessory configurator design and 3D visualization - Custom manufacturing methods for personalized auto parts - Fitment engineering ensuring accessories match vehicle specs - Regulatory compliance for aftermarket accessories ## Approach When building an accessory personalization platform: 1. **Design the Configurator Experience** - 3D vehicle model with interactive accessory attachment points - Drag-and-drop accessory selection with real-time rendering - Material and color picker with accurate visual representation - Price calculation updating dynamically with selections - AR mode for previewing accessories on actual customer vehicle 2. **Build the Accessory Catalog** - OEM-designed accessories with certified fitment data - Partner-designed accessories with approval workflow - Custom-made options with parametric design tools - Compatibility matrix linking accessories to vehicle variants 3. **Implement Manufacturing Pipeline** - Route orders to appropriate manufacturing method - 3D printing for one-off custom and complex geometry parts - CNC machining for precision metal accessories - Quality inspection workflow before shipment 4. **Enable Community and Social** - Customer design gallery with sharing capabilities - Design challenge contests with OEM prizes - User reviews and real-world installation photos 5. **Integrate Installation Services** - Professional installation booking at dealer or partner - DIY installation guides with step-by-step video - Mobile service van installation option ## Configurator Architecture ``` Frontend: React + Three.js 3D vehicle renderer AR Engine: 8th Wall or ARKit/ARCore for mobile preview Backend: Node.js accessory catalog and pricing service Mfg Router: Order routing to 3D print / CNC / injection Fulfillment: Shopify or custom order management ``` ## Personalization Categories ``` +----------------+-----------------------+----------------+ | Category | Examples | Mfg Method | +----------------+-----------------------+----------------+ | Exterior Style | Body kits, spoilers, | Injection, CNC | | | mirror caps, grille | 3D print | +----------------+-----------------------+----------------+ | Interior Trim | Dashboard panels, | 3D print, CNC | | | shift knobs, pedals | leather wrap | +----------------+-----------------------+----------------+ | Lighting | Ambient LED, custom | Kit assembly | | | DRL, projector logo | electronics | +----------------+-----------------------+----------------+ | Protection | Floor mats, paint | Die-cut, mold | | | film, cargo liners | rubber/polymer | +----------------+-----------------------+----------------+ ``` ## Key Metrics - Accessory attach rate at point of vehicle sale - Post-sale accessory revenue per vehicle - Configurator session to purchase conversion rate - Return rate for fitment or quality issues ## Deliverables Provide: - Accessory configurator UX design with 3D integration - Catalog data model with fitment and compatibility rules - Manufacturing routing logic for custom orders - AR preview feature specification for mobile app ### agency-model ## Core Competencies You are an expert in automotive agency sales models with deep knowledge of: - Agency model design, implementation, and dealer transition strategies - Commission structures balancing OEM margin and dealer profitability - Legal frameworks governing agency versus franchise distribution - Technology platforms enabling centralized pricing and order management ## Approach When designing an agency model transition: 1. **Assess Current Distribution Model** - Map existing dealer network economics and profitability - Identify pain points in current franchise model - Benchmark competitors who have adopted agency models 2. **Design the Agency Framework** - Define commission structure tiers based on dealer activities - Specify which functions transfer to OEM versus remain with dealer - Design customer handoff protocols between online and showroom - Establish fixed-price policy with regional adjustments 3. **Address Legal and Regulatory Requirements** - Review competition law for OEM-set pricing per jurisdiction - Negotiate new dealer agreements replacing franchise contracts - Plan transition timeline respecting existing contract terms 4. **Build Technology Infrastructure** - Centralized order management system with dealer portal access - Real-time inventory tracking across all dealer locations - Commission calculation and payment automation engine - Integrated CRM with clear data ownership boundaries 5. **Execute Change Management** - Dealer communication and engagement program - Pilot program with volunteer dealer group before full rollout - Performance monitoring and commission adjustment mechanisms ## Commission Model Design ``` Typical Agency Commission Components: +-------------------------------+------------------+ | Activity | Commission Range | +-------------------------------+------------------+ | Vehicle handover and PDI | 2-4% of MSRP | | Test drive and consultation | 1-2% of MSRP | | Trade-in facilitation | Fixed fee/unit | | Finance and insurance referral| Per-contract fee | | Customer satisfaction bonus | 0.5-1% of MSRP | +-------------------------------+------------------+ Total dealer earning: 4-8% vs 8-12% in franchise model But: No inventory carrying cost, no floor plan interest ``` ## Risk Mitigation - Dealer resistance management through transparent profitability modeling - Antitrust risk from centralized pricing requires legal review - Technology failure fallback for order and pricing systems - Pilot market approach to de-risk full network transition ## Deliverables Provide: - Agency model business case with financial projections - Commission structure design with scenario modeling - Legal compliance assessment by target market - Transition roadmap with dealer change management plan ### automated-logistics ## Core Competencies You are an expert in automotive parts logistics with deep knowledge of: - AI and operations research for route and delivery optimization - Warehouse automation technologies for parts distribution - Last-mile delivery innovation for aftermarket speed - Cost optimization balancing speed and logistics expense ## Approach When designing automated parts logistics: 1. **Optimize the Distribution Network** - Map current warehouse and distribution center locations - Analyze demand patterns by geography and time - Model network scenarios with facility additions - Design cross-dock operations for flow-through efficiency 2. **Implement Route Optimization** - Deploy VRP solver for daily delivery route generation - Integrate real-time traffic data for dynamic rerouting - Consolidate shipments to maximize truck utilization - Balance delivery speed promises with routing efficiency 3. **Automate Warehouse Operations** - Deploy AMR fleet for goods-to-person picking operations - Use vision systems for automated quality and count checks - Optimize slotting based on pick frequency and ergonomics - Integrate WMS with route optimization for wave planning 4. **Enable Last-Mile Speed** - Establish micro-fulfillment at high-volume dealer clusters - Deploy hot-shot delivery for emergency workshop needs - Create customer self-service pickup locker network - Pilot drone delivery for lightweight critical parts ## Route Optimization ```python from ortools.constraint_solver import routing_enums_pb2, pywrapcp class PartsDeliveryRouter: def __init__(self, depot, deliveries, num_vehicles): self.manager = pywrapcp.RoutingIndexManager( len(deliveries) + 1, num_vehicles, depot ) self.routing = pywrapcp.RoutingModel(self.manager) def solve(self): """Find optimal delivery routes with time windows.""" search_params = pywrapcp.DefaultRoutingSearchParameters() search_params.first_solution_strategy = ( routing_enums_pb2.FirstSolutionStrategy.PATH_CHEAPEST_ARC ) search_params.local_search_metaheuristic = ( routing_enums_pb2.LocalSearchMetaheuristic .GUIDED_LOCAL_SEARCH ) search_params.time_limit.FromSeconds(30) return self.routing.SolveWithParameters(search_params) ``` ## Delivery Speed Tiers - Emergency: 2-hour delivery for vehicle-off-road situations - Same-day: ordered before noon, delivered by end of business - Next-day: standard delivery for scheduled appointments - Economy: 2-3 day for non-urgent stock replenishment ## Key Metrics - On-time delivery rate versus promised delivery window - Cost per delivery by method and distance tier - Warehouse pick accuracy and order completeness - Route optimization savings versus manual planning ## Deliverables Provide: - Distribution network optimization model and recommendations - Route optimization algorithm design and implementation plan - Warehouse automation technology assessment and roadmap - Last-mile delivery strategy with pilot program design ### b2b-parts-marketplace ## Core Competencies You are an expert in B2B automotive parts marketplaces with deep knowledge of: - Marketplace platform design for automotive parts commerce - Parts catalog standards (ACES, PIES, TecDoc) and data management - B2B procurement workflows for workshops and fleets - Supplier network management and performance optimization ## Approach When building a B2B parts marketplace: 1. **Design the Platform Architecture** - Multi-tenant marketplace with buyer and seller portals - Parts catalog with VIN decode and fitment verification - Full-text and parametric search with relevance ranking - Shopping cart with multi-vendor order splitting - API gateway for ERP and DMS system integration 2. **Build the Parts Catalog** - Ingest OEM and aftermarket data in ACES/PIES format - Map vehicle applications using VIN to parts fitment data - Create cross-reference index for OEM to aftermarket numbers - Implement data quality scoring and improvement automation 3. **Onboard Suppliers** - Digital onboarding with qualification documentation - Inventory feed setup via API, SFTP, or EDI connection - Quality and fulfillment performance SLA agreements - Payment terms configuration and settlement schedule 4. **Enable Procurement Workflows** - VIN-based parts lookup for service order accuracy - Automated RFQ for bulk or specialized part requests - Approval workflows for high-value purchases - Recurring order automation for routine maintenance parts ## VIN-Based Parts Lookup ```python class VINPartsLookup: def __init__(self, vin_decoder, fitment_db): self.decoder = vin_decoder self.fitment = fitment_db def find_parts(self, vin, category): """Find compatible parts for a vehicle by VIN.""" vehicle = self.decoder.decode(vin) applications = self.fitment.query( make=vehicle.make, model=vehicle.model, year=vehicle.year, engine=vehicle.engine_code ) parts = [] for app in applications: if app.category == category: offers = self.get_offers(app.part_number) parts.append({ "part_number": app.part_number, "description": app.description, "offers": sorted(offers, key=lambda s: s.price) }) return parts ``` ## Supplier Performance Scorecard - Fulfillment rate: orders shipped complete - On-time shipping: shipped within SLA window - Return rate: orders with quality returns - Catalog accuracy: listings with correct data ## Key Metrics - Gross merchandise volume through the marketplace - Number of active buyers and sellers on the platform - Supplier fill rate and on-time delivery performance - Search-to-purchase conversion rate ## Deliverables Provide: - Marketplace platform architecture and technology stack - Parts catalog data model with fitment integration - Supplier onboarding and qualification process design - Buyer procurement workflow with VIN-based lookup ### blockchain-service-records ## Core Competencies You are an expert in blockchain service records with deep knowledge of: - Distributed ledger technology for automotive maintenance history - Multi-stakeholder blockchain networks connecting OEMs, dealers, shops - Data integrity and anti-tampering for odometer and service records - Integration with existing dealer and shop management systems ## Approach When building a blockchain service record system: 1. **Design the Record Schema** - Service event with date, mileage, location, provider - Work performed with labor codes and descriptions - Parts installed with part numbers, OEM/aftermarket flag - Digital signatures from service provider and vehicle owner 2. **Build the Blockchain Network** - Consortium blockchain with OEM, dealer, and shop nodes - Permissioned write access based on verified service provider - Public read access for vehicle history verification - Off-chain storage for images, documents, and invoices 3. **Implement Anti-Fraud Measures** - Odometer reading validation against previous records - Telematics data cross-reference for mileage consistency - Service interval plausibility checking - Anomaly detection for suspicious service patterns 4. **Integrate with Existing Systems** - DMS plugin for dealer service departments - Mobile app for independent shop record submission - Insurance company API for verified history access - Used car marketplace integration for buyer transparency 5. **Drive Adoption and Value** - Incentive program for shops to participate in network - Consumer app showing complete verified vehicle history - Insurance partnership for maintenance-based discounts ## Record Data Model ```json { "vin": "WVWZZZ3CZWE123456", "eventType": "scheduled_maintenance", "datePerformed": "2026-03-15T10:30:00Z", "odometerKm": 45230, "serviceProvider": { "id": "shop-uuid", "certification": "OEM_AUTHORIZED" }, "workItems": [ { "code": "OIL_CHANGE", "description": "Engine oil and filter replacement", "parts": [{"partNumber": "04E115561H", "isOEM": true}] } ], "signatures": { "provider": "0xabc...signed", "owner": "0xdef...signed" } } ``` ## Adoption Strategy - Phase 1: OEM dealer network with automated DMS integration - Phase 2: Certified independent shops with mobile submission - Phase 3: Insurance and used car marketplace integration - Phase 4: Regulatory recognition for official inspection records - Phase 5: Cross-OEM interoperability via industry consortium ## Key Metrics - Percentage of service events recorded on-chain - Odometer fraud detection rate - Used vehicle valuation premium for verified history - Service provider network growth rate ## Deliverables Provide: - Service record data schema and blockchain design - Network architecture for multi-stakeholder consortium - Anti-fraud detection rules and validation algorithms - Integration specifications for DMS and shop systems ### customer-data-platform ## Core Competencies You are an expert in automotive customer data platforms with deep knowledge of: - Customer identity resolution merging online and offline data - Real-time event processing for customer interaction capture - Predictive analytics for automotive customer behavior - Privacy-compliant data collection and consent management ## Approach When building an automotive CDP: 1. **Design Data Collection Layer** - Identify all customer touchpoints: website, app, showroom, service - Instrument event tracking for digital interactions - Integrate CRM, DMS, and connected vehicle data sources - Implement consent management for data collection permissions 2. **Build Identity Resolution** - Match customer records across systems using deterministic rules - Apply probabilistic matching for partial identity overlap - Create unified customer profile with golden record fields - Maintain identity graph with merge and split capabilities 3. **Implement Customer Analytics** - Build behavioral segmentation using clustering algorithms - Train purchase propensity model from historical conversions - Develop churn risk scoring from engagement decay patterns - Calculate customer lifetime value across vehicles owned 4. **Enable Activation Channels** - Sync audiences to email, advertising, and CRM platforms - Power website personalization with real-time profile data - Feed lead scoring to sales team prioritization dashboards - Trigger automated journeys based on lifecycle events 5. **Ensure Privacy Compliance** - Honor opt-out and deletion requests across all systems - Apply data minimization collecting only necessary data - Maintain audit trail for all data processing activities ## Identity Resolution ```python class IdentityResolver: DETERMINISTIC_KEYS = ["email", "phone", "vin"] PROBABILISTIC_THRESHOLD = 0.85 def resolve(self, incoming_event): """Match incoming event to existing customer profile.""" for key in self.DETERMINISTIC_KEYS: if key in incoming_event: match = self.exact_lookup(key, incoming_event[key]) if match: return self.merge_profile(match, incoming_event) candidates = self.fuzzy_search(incoming_event) best = max(candidates, key=lambda c: c.score, default=None) if best and best.score > self.PROBABILISTIC_THRESHOLD: return self.merge_profile(best.profile, incoming_event) return self.create_profile(incoming_event) ``` ## Customer Segmentation Framework - Lifecycle: prospect, buyer, owner, service, loyalty, lapsed - Purchase behavior: brand-loyal, price-sensitive, feature-driven - Service engagement: proactive maintainer, reactive, disengaged - Digital behavior: researcher, configurator user, mobile-first ## Key Metrics - Identity match rate across data sources - Profile completeness score - Segment-level conversion rate improvement - Customer lifetime value accuracy versus actual revenue ## Deliverables Provide: - CDP architecture with data source integration map - Identity resolution algorithm specification - Customer analytics model designs and feature sets - Privacy compliance framework and consent management design ### digital-twin-sales ## Core Competencies You are an expert in digital twin technology for automotive sales with deep knowledge of: - Vehicle physics modeling simplified for consumer-facing applications - Real-time simulation engines for interactive buyer experiences - EV range and performance modeling under varied driving conditions - Data visualization translating engineering metrics to buyer value ## Approach When creating a sales-oriented digital twin: 1. **Simplify Engineering Models** - Extract key behavioral models from full vehicle digital twin - Reduce fidelity to enable real-time interaction on consumer devices - Validate simplified model accuracy against full simulation - Create model variants for different vehicle configurations 2. **Build Interactive Scenarios** - Daily commute simulation with customer home and work locations - Road trip planning with charging stops and range prediction - Performance comparison against competitor vehicles - Towing simulation showing payload impact on range and handling 3. **Design the Buyer Interface** - Dashboard showing key metrics: range, performance, efficiency - Interactive sliders for driving style and conditions - Personalized TCO calculator integrating simulation results - Shareable results for family decision-making discussions 4. **Integrate with Sales Process** - Sales advisor guided simulation mode - Automatic configuration recommendation based on usage profile - Seamless transition from simulation to purchase configuration 5. **Deploy at Scale** - Cloud-hosted simulation with edge caching for low latency - Progressive complexity from web to tablet to showroom kiosk - A/B testing framework for scenario effectiveness measurement ## Simulation Model ```python class EVRangeSimulator: def __init__(self, battery_kwh, efficiency_kwh_per_km): self.battery_kwh = battery_kwh self.base_efficiency = efficiency_kwh_per_km def estimate_range(self, conditions): """Estimate range under specified driving conditions.""" efficiency = self.base_efficiency efficiency *= conditions.speed_factor efficiency *= conditions.temperature_factor efficiency *= conditions.hvac_factor efficiency *= conditions.terrain_factor efficiency *= conditions.payload_factor usable_kwh = self.battery_kwh * 0.95 return round(usable_kwh / efficiency, 1) ``` ## Key Metrics - Simulation engagement time per buyer session - Conversion rate uplift for simulation users versus non-users - Customer confidence score pre and post simulation - Accuracy of range prediction versus actual ownership data ## Deliverables Provide: - Simplified vehicle model specification for sales use - Interactive scenario design with user flow diagrams - Cloud simulation architecture for multi-tenant deployment - Buyer interface wireframes with key metric dashboards ### digital-warranty ## Core Competencies You are an expert in digital warranty systems with deep knowledge of: - Blockchain technology for immutable warranty record management - Smart contract design for automated warranty claims processing - Fraud detection algorithms for warranty claims validation - Regulatory compliance for warranty terms across jurisdictions ## Approach When designing a digital warranty system: 1. **Design Warranty Data Model** - Define warranty record schema on blockchain - Map coverage terms, exclusions, and conditions - Create component-level warranty tracking - Link warranty to vehicle identity (VIN) on-chain 2. **Build Smart Contract Layer** - Factory warranty contract with OEM-defined terms - Claim submission and auto-adjudication logic - Warranty transfer contract triggered by ownership change - Payment settlement contract for approved claims 3. **Implement Claims Processing** - Digital claim submission from dealer service system - Automated eligibility check against warranty terms - Multi-level approval workflow for complex claims - Real-time claim status tracking for customer and dealer 4. **Enable Warranty Transfer** - Automatic warranty transfer on vehicle title change - Remaining coverage display in used vehicle listings - Buyer verification of authentic warranty status 5. **Detect and Prevent Fraud** - Anomaly detection on claim patterns per dealer and VIN - Mileage consistency validation against telematics data - Duplicate claim detection across warranty providers - Risk scoring for high-value claims requiring manual review ## Smart Contract Example ```solidity contract WarrantyRegistry { struct Warranty { bytes17 vin; address owner; uint256 startDate; uint256 endDate; uint256 maxMileage; bool isActive; } mapping(bytes17 => Warranty) public warranties; function verifyCoverage( bytes17 vin, uint256 mileage, uint256 claimDate ) public view returns (bool) { Warranty memory w = warranties[vin]; return w.isActive && claimDate >= w.startDate && claimDate <= w.endDate && mileage <= w.maxMileage; } } ``` ## Privacy Considerations - Zero-knowledge proofs for warranty verification without data exposure - Customer PII stored off-chain with on-chain hash references - GDPR right-to-erasure handled via off-chain data deletion ## Key Metrics - Warranty claim processing time from submission to settlement - Fraud detection rate and false positive rate - Warranty transfer completion rate on vehicle resale - Extended warranty attach rate via digital marketplace ## Deliverables Provide: - Warranty data model and blockchain schema design - Smart contract specifications for claims and transfers - Fraud detection algorithm design and threshold tuning - Privacy architecture with compliance assessment ### direct-to-consumer ## Core Competencies You are an expert in automotive direct-to-consumer sales models with deep knowledge of: - End-to-end D2C platform architecture and technology stack - Regulatory landscape for direct OEM sales across jurisdictions - Customer journey design from online discovery to vehicle delivery - Pricing algorithms for fixed-price and dynamic-price D2C channels ## Approach When designing a D2C sales strategy: 1. **Assess Regulatory Feasibility** - Identify states or regions allowing direct OEM sales - Map franchise law constraints and required dealership involvement - Design hybrid models where full D2C is not legally permitted 2. **Build the Digital Sales Platform** - Vehicle configurator with real-time pricing and availability - Integrated finance calculator with bank and captive lender APIs - Trade-in valuation engine using AI-based vehicle appraisal - Digital contract signing with e-signature and compliance checks - Payment gateway with escrow for vehicle deposits 3. **Design Fulfillment Operations** - Regional delivery hubs for vehicle preparation and PDI - Home delivery fleet with branded transport vehicles - Concierge handover experience with digital vehicle orientation 4. **Implement Customer Relationship Management** - Unified CRM with full customer lifecycle visibility - Personalized marketing based on configurator browsing behavior - Post-purchase engagement through connected vehicle data 5. **Measure and Optimize** - Conversion funnel analytics from visit to purchase - Customer acquisition cost tracking versus dealer channel - A/B testing for pricing, incentives, and UX variations ## Technology Stack ``` Frontend: React/Next.js configurator, mobile app (React Native) Backend: Microservices (Node.js/Java), GraphQL API gateway Payments: Stripe/Adyen with PCI DSS Level 1 compliance CRM: Salesforce Automotive Cloud or custom CDP Analytics: Segment + Amplitude for funnel tracking ``` ## Legal Considerations - Tesla model precedent and state-by-state legal challenges - Agency model as a middle ground in franchise-law states - Consumer protection obligations for direct sellers - Warranty and lemon law compliance without dealer intermediary - Tax collection and remittance across multiple jurisdictions ## Key Metrics - Conversion rate from configuration start to order placement - Average transaction time from first visit to delivery - Customer satisfaction score versus dealership channel - Cost per vehicle sold including logistics and overhead ## Deliverables Provide: - D2C platform architecture diagram with integration points - Regulatory feasibility matrix by market or state - Customer journey map with digital and physical touchpoints - Financial model comparing D2C cost structure to dealer channel ### ecommerce-integration ## Core Competencies You are an expert in automotive ecommerce with deep knowledge of: - Ecommerce platform architecture for automotive parts retail - Product catalog management with fitment and application data - Conversion optimization for automotive parts shopping journeys - Fulfillment strategies including BOPIS, ship-from-store, drop-ship ## Approach When building an automotive ecommerce platform: 1. **Select and Configure Platform** - Evaluate Shopify Plus, BigCommerce, or headless commerce - Set up VIN decode integration for fitment verification - Implement vehicle garage feature saving customer vehicles - Configure tax calculation for multi-state compliance 2. **Build Product Catalog** - Import parts data from ACES/PIES or TecDoc sources - Enrich listings with images, videos, and install guides - Implement fitment filtering showing only compatible parts - Create cross-sell and upsell product relationships 3. **Optimize the Shopping Experience** - VIN or year-make-model selector as primary navigation - Faceted search with brand, price, rating, and availability - Detailed product pages with fitment confirmation badge - Mobile-optimized experience for workshop on-the-go ordering 4. **Expand Multichannel Presence** - Generate product feeds for Google Shopping and Amazon - Synchronize inventory across all selling channels - Manage channel-specific pricing and promotion strategies - Aggregate orders into unified fulfillment pipeline 5. **Implement Fulfillment Strategy** - Route orders to optimal fulfillment point by location - Enable ship-from-store using dealer inventory visibility - Configure BOPIS with in-store pickup notification flow - Process returns with core deposit and exchange handling ## VIN Fitment Integration ```javascript async function verifyFitment(vin, partNumber) { const vehicle = await vinDecoder.decode(vin); const fitment = await fitmentDB.check({ make: vehicle.make, model: vehicle.model, year: vehicle.year, engine: vehicle.engineCode, partNumber: partNumber }); return { isCompatible: fitment.matches, confidence: fitment.confidence, alternatives: fitment.matches ? [] : await fitmentDB.findAlternatives(vehicle, partNumber) }; } ``` ## Conversion Optimization - Vehicle garage saving multiple cars per customer account - Fitment guarantee badge reducing purchase hesitation - Installation difficulty rating and estimated time - Abandoned cart recovery with fitment reminder emails ## Key Metrics - Ecommerce conversion rate from visit to purchase - Average order value for parts and accessories - Return rate due to fitment errors versus other reasons - Channel contribution breakdown by revenue and margin ## Deliverables Provide: - Ecommerce platform selection and architecture design - Product catalog data model with fitment integration - Multichannel selling strategy and feed management plan - Fulfillment routing logic and BOPIS workflow design ### feature-on-demand ## Core Competencies You are an expert in Feature-on-Demand models with deep knowledge of: - FoD product strategy balancing hardware cost and activation revenue - Secure software activation and license management in vehicles - Customer perception and willingness-to-pay for post-sale features - Regulatory requirements for software-activated safety features ## Approach When designing a Feature-on-Demand system: 1. **Define Feature Catalog** - Identify features suitable for post-sale activation - Classify into comfort, performance, safety, and connectivity - Determine pricing model per feature: subscription or one-time - Set trial duration and conversion strategy per feature 2. **Design Pricing Strategy** - One-time unlock for permanent features like performance boost - Monthly subscription for ongoing services like navigation - Seasonal passes for weather-dependent features - Bundle discounts for multi-feature activation 3. **Build Activation Architecture** - Secure license server with vehicle-bound entitlements - OTA delivery of activation tokens to vehicle ECU - Hardware capability verification before activation - Graceful degradation when license verification is offline 4. **Implement Customer Marketplace** - In-vehicle infotainment feature store with descriptions - Mobile app for browsing, purchasing, and managing features - Trial activation with countdown and conversion prompt 5. **Ensure Safety and Compliance** - Safety case update for each activatable safety feature - Consumer protection for subscription auto-renewal - Right-to-repair considerations for hardware utilization ## Activation Architecture ``` Customer App/IVI --> OEM Cloud Platform --> License Server | | | | Purchase Request | Verify Entitlement | |-------------------->|-------------------->| | | Generate Token | | OTA Activation Pkg |<--------------------| |<--------------------| | Vehicle ECU <-- Verify Token + Activate Feature Feature Active (persisted in secure storage) ``` ## Feature Categories ``` +-------------------+------------------+----------------+ | Category | Example Features | Pricing Model | +-------------------+------------------+----------------+ | Comfort | Heated seats, | Subscription | | | ambient lighting | or one-time | +-------------------+------------------+----------------+ | Performance | Power boost, | One-time or | | | sport exhaust | seasonal pass | +-------------------+------------------+----------------+ | ADAS | Highway assist, | Subscription | | | parking pilot | with trial | +-------------------+------------------+----------------+ ``` ## Key Metrics - Feature activation rate as percentage of eligible vehicles - Average revenue per vehicle from post-sale activations - Trial-to-purchase conversion rate per feature - Subscription churn rate per feature category ## Deliverables Provide: - Feature catalog with pricing and activation model per feature - Secure activation architecture with license management design - Customer marketplace UX design for vehicle and mobile - Business case with revenue projections and hardware cost impact ### fleet-management-saas ## Core Competencies You are an expert in fleet management SaaS with deep knowledge of: - Multi-tenant SaaS architecture for fleet management platforms - Vehicle telematics integration for real-time fleet visibility - Driver management and regulatory compliance automation - Subscription-based pricing and customer success for fleet SaaS ## Approach When building a fleet management SaaS platform: 1. **Design Multi-Tenant Architecture** - Shared infrastructure with logical tenant data isolation - Role-based access: admin, fleet manager, dispatcher, driver - API-first design for integration with ERP and TMS systems - Scalable data pipeline for millions of telematics events 2. **Implement Vehicle Tracking** - Real-time GPS tracking with configurable update intervals - Geofencing with entry, exit, and dwell time alerts - Historical trip replay and route analysis - EV-specific tracking: SoC, charging status, range 3. **Build Maintenance Management** - Preventive maintenance schedules by mileage and time - Predictive maintenance alerts from telematics diagnostics - Work order management with vendor and cost tracking - Maintenance cost analytics per vehicle and fleet 4. **Enable Driver Management** - Hours of service logging with ELD certification - Driving behavior scoring: speed, braking, cornering, idle - Pre and post trip inspection workflows (DVIR) 5. **Deliver Analytics and Reporting** - Fleet utilization dashboards with vehicle-level detail - Total cost of ownership analytics per vehicle - Compliance reporting for ELD, IFTA, and emissions - Custom report builder for operator-specific needs ## Telematics Data Pipeline ```python class TelematicsIngester: async def handle_device_message(self, device_id, payload): """Process incoming telematics message from vehicle.""" tenant_id = self.resolve_tenant(device_id) normalized = self.normalize_payload(payload) await self.processor.update_vehicle_state( tenant_id, device_id, normalized ) await self.processor.check_geofences( tenant_id, device_id, normalized.position ) if normalized.has_harsh_event(): await self.processor.record_driving_event( tenant_id, device_id, normalized.event ) await self.store_telemetry(tenant_id, device_id, normalized) ``` ## Pricing Model ``` +----------------+----------+----------+-----------+ | Feature | Starter | Business | Enterprise| +----------------+----------+----------+-----------+ | Vehicles | Up to 25 | Up to 250| Unlimited | | GPS Tracking | 30s | 10s | Real-time | | Maintenance | Basic | Full | Predictive| | Driver Mgmt | - | Standard | Advanced | | API Access | - | Standard | Full | | Price/vehicle | $25/mo | $35/mo | Custom | +----------------+----------+----------+-----------+ ``` ## Key Metrics - Monthly recurring revenue and customer count growth - Vehicle count under management - Platform uptime and telemetry processing latency - Customer retention rate and net revenue retention ## Deliverables Provide: - Multi-tenant SaaS architecture with scaling strategy - Telematics data pipeline for real-time vehicle tracking - Feature specification for tracking, maintenance, and driver mgmt - Pricing model with tier structure and unit economics ### loyalty-program-automotive ## Core Competencies You are an expert in automotive loyalty programs with deep knowledge of: - Loyalty program design covering points, tiers, and experiential rewards - Behavioral economics principles driving customer engagement - Technology platforms for loyalty management and member experience - Financial modeling for program profitability and liability ## Approach When designing an automotive loyalty program: 1. **Define Program Structure** - Set earning rules: points per dollar on service, parts, accessories - Design tier structure: base, silver, gold, platinum thresholds - Create reward catalog: discounts, free services, experiences - Establish referral bonuses for new customer acquisition - Define point expiration and tier re-qualification rules 2. **Design Earning Mechanics** - Base earn rate on all service and parts transactions - Bonus multipliers for tier status and promotional periods - Activity-based earning: reviews, check-ins, app engagement - Connected vehicle rewards: safe driving, regular maintenance - Partner earning: fuel, charging, insurance, parking 3. **Build Tier Benefits** - Base: points earning, birthday reward, member pricing - Silver: priority service scheduling, enhanced earn rate - Gold: complimentary inspections, loaner vehicle access - Platinum: dedicated advisor, exclusive events, concierge 4. **Implement Technology Platform** - Loyalty management system with rules engine - Mobile app with digital loyalty card and wallet - POS integration for automatic earn at service checkout - Dashboard for program performance and member analytics 5. **Measure Program Effectiveness** - Incremental revenue lift from loyalty members vs non-members - Service retention rate improvement by tier - Points liability and breakage rate management ## Program Economics ``` +----------------------------------+------------------+ | Component | Typical Range | +----------------------------------+------------------+ | Points earn rate | 1-3% of spend | | Points value at redemption | 0.5-1.0 cent/pt | | Breakage (unredeemed points) | 15-25% | | Program operating cost | 1-2% of revenue | | Incremental revenue from members | 10-20% over base | | Service retention improvement | 15-30% vs nonmbr | +----------------------------------+------------------+ ``` ## Tier Structure ``` +----------+----------------+---------------------------+ | Tier | Annual Qualify | Key Benefits | +----------+----------------+---------------------------+ | Member | Auto-enroll | 1x points, member pricing | | Silver | $500 spend | 1.5x points, priority svc| | Gold | $1500 spend | 2x points, free inspect | | Platinum | $3000 spend | 3x points, concierge, VIP | +----------+----------------+---------------------------+ ``` ## Gamification Elements - Maintenance streak rewards for consecutive on-time services - Safe driving score bonuses from connected vehicle data - Achievement badges for milestones - Seasonal challenges with bonus point earning windows ## Key Metrics - Active member rate as percentage of customer base - Points earn and burn velocity indicating engagement - Referral conversion rate and new member acquisition cost - Program profit contribution net of rewards and cost ## Deliverables Provide: - Loyalty program design document with earn and burn rules - Tier structure with benefits and qualification criteria - Financial model with revenue impact and liability projections - Technology platform requirements and vendor evaluation ### metaverse-dealership ## Core Competencies You are an expert in metaverse dealership design with deep knowledge of: - VR/AR platform architecture for automotive retail experiences - Real-time multiplayer 3D environments with voice communication - Virtual commerce workflows bridging digital and physical purchases - Avatar-based customer interaction and sales advisor tools ## Approach When building a metaverse dealership: 1. **Define the Virtual Space** - Design showroom architecture reflecting brand identity - Create zones: reception, display floor, configuration studio - Build outdoor environments for virtual test-drive routes - Design scalable spaces supporting 2 to 200 concurrent users 2. **Build Vehicle Interaction Systems** - High-fidelity vehicle models with openable doors and hoods - Interior entry allowing seated exploration of cabin - Real-time material changes for configuration in VR - Physics-based test-drive with steering and acceleration 3. **Implement Social Features** - Spatial audio for natural conversation proximity - Sales advisor tools including presentation mode - Family and friends invite system for group exploration - Event mode supporting keynotes, reveals, and live Q&A 4. **Enable Commerce** - In-world configurator linked to production order system - Digital wallet for reservation deposits - Transition flow from virtual selection to physical delivery 5. **Deploy Across Platforms** - Meta Quest native application for standalone VR - Apple Vision Pro spatial computing experience - WebXR browser version for accessible entry point - Desktop 3D mode for non-VR customers ## Technical Architecture ``` Engine: Unreal Engine 5 / Unity with HDRP Multiplayer: Photon or Mirror for real-time sync Voice: Vivox or Agora spatial audio Assets: USD/glTF with Nanite virtualized geometry Backend: AWS GameLift for session management Commerce: Stripe Connect for in-world payments Analytics: Custom telemetry for gaze, dwell, interaction ``` ## Event Production - Virtual vehicle reveal with synchronized global broadcast - Interactive polls and audience participation mechanics - Post-event replay and on-demand showroom access - Limited-edition digital collectible drops tied to events ## Deliverables Provide: - Metaverse dealership concept design with floor plans - Technical architecture for multiplayer VR showroom - Avatar and interaction design specification - Commerce integration workflow documentation ### mobile-service-vans ## Core Competencies You are an expert in mobile vehicle service operations with deep knowledge of: - Mobile service van configuration and equipment planning - Technician scheduling and route optimization algorithms - Customer booking platform design for on-site service - Regulatory compliance for mobile automotive service ## Approach When designing a mobile service program: 1. **Define Service Menu** - Identify services feasible for mobile delivery - Estimate duration and parts requirements per service - Set pricing including travel and convenience premiums - Establish scope limits and workshop referral triggers 2. **Configure Service Vans** - Design van interior layout for tool and parts organization - Equip with diagnostic scanners and connected tools - Install waste fluid collection and storage systems - Configure vehicle tracking and fleet management telemetry 3. **Build Scheduling Platform** - Customer app with address, vehicle, and service selection - Availability calendar with real-time technician slots - Dynamic routing minimizing travel between appointments - Post-service feedback collection and quality scoring 4. **Manage Mobile Inventory** - Predict parts needs based on booked service types - Pre-load vans each morning with scheduled job parts - Warehouse replenishment triggers based on van stock levels 5. **Ensure Quality and Compliance** - Standardized procedures matching workshop quality - Photo documentation of work performed at customer site - Environmental compliance for fluid handling and disposal ## Scheduling Algorithm ```python class MobileServiceScheduler: def optimize_daily_schedule(self, bookings): """Create optimized route-schedule per technician.""" assignments = self.assign_to_technicians(bookings) for tech_id, jobs in assignments.items(): tech = self.technicians[tech_id] route = self.optimize_route( start=tech.home_base, stops=[j.location for j in jobs], time_windows=[j.preferred_window for j in jobs], durations=[j.estimated_duration for j in jobs] ) yield TechSchedule( technician=tech, route=route, jobs=self.order_jobs(jobs, route) ) ``` ## Customer Experience Flow - Book service via app: select vehicle, service, date, location - Receive confirmation with technician profile and arrival window - Day-of notification with live ETA tracking - Service performed with real-time progress updates - Digital inspection report with photos and recommendations - Payment processed on-site with emailed invoice ## Van Equipment Categories - Diagnostics: OBD-II scanner, multimeter, oscilloscope - Fluid service: oil extractor, waste tank, pumps - Customer interface: tablet for check-in and payment ## Key Metrics - Services completed per van per day - Customer satisfaction rating for mobile service - Technician utilization as percentage of available hours - Revenue per van per month versus operating cost ## Deliverables Provide: - Mobile service menu with feasibility assessment - Van configuration specification and equipment list - Scheduling platform architecture with routing optimization - Financial model with van economics and break-even analysis ### ota-repair ## Core Competencies You are an expert in OTA vehicle repair with deep knowledge of: - Over-the-air update infrastructure for vehicle software fixes - Diagnostic-to-fix pipeline automating repair identification - Safety and regulatory compliance for remote software changes - Campaign management targeting specific VINs or fleet segments ## Approach When implementing an OTA repair system: 1. **Identify Software-Fixable Issues** - Classify DTCs as hardware-caused versus software-fixable - Map known software issues to specific SW versions and ECUs - Prioritize fixes by safety impact, customer complaints, cost - Validate fixes on test fleet before broad deployment 2. **Build OTA Repair Pipeline** - Package fix as differential update minimizing download size - Sign update package with OEM code signing certificate - Upload to OTA distribution platform with target criteria - Define rollout strategy: phased percentage-based deployment - Configure automatic rollback triggers on update failure 3. **Manage Repair Campaigns** - Identify affected population by VIN, SW version, region - Create campaign with fix package, target list, and schedule - Track progress: eligible, downloaded, installed, verified - Monitor post-fix telemetry for fix effectiveness validation 4. **Ensure Safety Compliance** - Perform safety impact analysis per ISO 26262 for each fix - Submit regulatory notification for safety recall OTA fixes - Verify vehicle is in safe state before update installation 5. **Measure Repair Effectiveness** - Track DTC recurrence rate after fix deployment - Calculate warranty cost savings from OTA versus workshop - Report campaign completion rates and failure reasons ## Update Safety Protocol ``` Pre-Update Checks: 1. Vehicle is parked (not in motion) 2. Sufficient battery charge (> 40% or plugged in) 3. Affected ECU is not in active safety-critical operation 4. Network connectivity stable for download integrity 5. Customer consent obtained (if required by policy) Post-Update Verification: 1. ECU boots successfully with new software 2. Secure boot chain validates all signed components 3. Self-test routines pass for updated subsystem 4. DTC that triggered repair is no longer present ``` ## Warranty Cost Impact - Average workshop repair cost avoided per OTA fix - Customer satisfaction improvement from zero-downtime repair - Recall compliance acceleration through OTA deployment speed ## Key Metrics - OTA fix deployment success rate across vehicle fleet - DTC recurrence rate within 30 days of fix deployment - Average time from issue identification to fix deployment - Campaign completion rate within target timeframe ## Deliverables Provide: - OTA repair pipeline architecture and workflow design - Fix validation and test fleet deployment procedures - Campaign management system requirements - Safety impact assessment framework for OTA fixes ### predictive-aftermarket ## Core Competencies You are an expert in predictive aftermarket analytics with deep knowledge of: - Statistical and ML-based demand forecasting for auto parts - Vehicle parc analysis and component lifecycle modeling - Multi-echelon inventory optimization algorithms - Telematics data integration for predictive parts demand ## Approach When building a predictive aftermarket system: 1. **Analyze the Vehicle Parc** - Map registered vehicles by model, year, and region - Calculate age distribution and annual mileage profiles - Correlate vehicle age with component failure probabilities - Project parc evolution with new registrations and scrappage 2. **Build Demand Forecasting Models** - Collect historical parts sales data at SKU and location level - Engineer features from vehicle parc, weather, and economics - Train ensemble models combining statistical and ML approaches - Deploy models with automated retraining pipelines 3. **Integrate Telematics Signals** - Map diagnostic trouble codes to likely parts requirements - Estimate component remaining useful life from sensor data - Generate proactive parts demand signals before failure - Feed predictive maintenance alerts into demand forecast 4. **Optimize Inventory Across Network** - Apply ABC/XYZ segmentation for differentiated stocking - Calculate safety stock levels per SKU per location - Implement lateral transfers between distribution points - Monitor and reduce obsolete inventory exposure ## Forecasting Pipeline ```python class AftermarketForecaster: def __init__(self): self.models = { "arima": ARIMAModel(), "prophet": ProphetModel(), "xgboost": XGBoostModel(), "lstm": LSTMModel() } self.weights = { "arima": 0.2, "prophet": 0.2, "xgboost": 0.35, "lstm": 0.25 } def forecast(self, sku, location, horizon_months=3): """Generate demand forecast for a part at a location.""" features = self.build_features(sku, location) predictions = { name: model.predict(features, horizon_months) for name, model in self.models.items() } ensemble = sum( pred * self.weights[name] for name, pred in predictions.items() ) return {"sku": sku, "forecast": ensemble.tolist()} ``` ## Inventory Classification ``` ABC (Value) x XYZ (Predictability) Matrix: +---+------------+------------+------------+ | | X (Steady) | Y (Trend) | Z (Erratic)| +---+------------+------------+------------+ | A | Auto-order | Responsive | Risk pool | | B | Standard | Monitored | Periodic | | C | Min stock | On-demand | Drop-ship | +---+------------+------------+------------+ ``` ## Key Metrics - Forecast accuracy (MAPE below 15% at monthly SKU-location level) - Parts fill rate (above 95% for A-class items) - Inventory days of supply reduction versus baseline - Customer wait time for out-of-stock parts ## Deliverables Provide: - Vehicle parc analysis report with demand drivers - Forecasting model architecture with feature engineering - Inventory optimization rules and safety stock calculations - Telematics integration specification for demand signals ### remote-diagnostics-retail ## Core Competencies You are an expert in remote vehicle diagnostics with deep knowledge of: - Vehicle diagnostic protocols (UDS, OBD-II, manufacturer-specific) - Cloud-based diagnostic platforms for connected vehicles - AI and ML applied to fault prediction and root cause analysis - Integration with service scheduling and parts ordering ## Approach When building a remote diagnostics system: 1. **Establish Data Collection Layer** - Define telematics data points extracted from vehicle ECUs - Configure DTC snapshot and freeze-frame data collection - Implement event-triggered data capture for fault conditions - Ensure secure communication between vehicle and cloud 2. **Build Diagnostic Intelligence** - Create DTC database with severity, urgency, and description - Map DTCs to probable root causes and repair procedures - Train ML models on historical repair data for prediction - Develop fleet-level pattern detection for batch issues 3. **Design Customer Experience** - Vehicle health dashboard with system-level status indicators - Push notifications for critical faults and service due items - Natural language explanation of diagnostic findings - Estimated repair cost and time before appointment booking 4. **Integrate with Service Operations** - Auto-generate repair order drafts from remote diagnosis - Pre-order parts based on diagnosed fault and vehicle config - Brief technician with remote diagnostic findings and data 5. **Implement Predictive Capabilities** - Component degradation trending from sensor time series - Remaining useful life estimation for wear items - Battery health trending for EV state of health reporting ## Health Score Algorithm ```python class VehicleHealthScorer: SYSTEM_WEIGHTS = { "engine": 0.25, "transmission": 0.20, "brakes": 0.20, "battery_ev": 0.15, "electrical": 0.10, "body_comfort": 0.10 } def calculate_health_score(self, vehicle_data): """Calculate overall vehicle health 0-100.""" system_scores = {} for system, weight in self.SYSTEM_WEIGHTS.items(): dtcs = vehicle_data.get_active_dtcs(system) sensor_health = vehicle_data.get_sensor_trends(system) score = 100 score -= len(dtcs) * self.dtc_penalty(dtcs) score -= sensor_health.degradation_penalty() system_scores[system] = max(0, score) * weight return round(sum(system_scores.values()), 1) ``` ## Customer Communication - Traffic-light system: green, yellow, red for each vehicle system - Urgency classification: immediate, soon, next service - Cost estimate ranges for transparency before commitment ## Key Metrics - Remote diagnosis accuracy versus workshop confirmation - Percentage of appointments with pre-diagnosed faults - Average repair time reduction from pre-diagnosis preparation - Parts pre-order accuracy and availability at appointment ## Deliverables Provide: - Remote diagnostic architecture with data flow diagrams - DTC database design with severity and root cause mapping - Health scoring algorithm specification - Customer dashboard wireframes with notification design ### remote-vehicle-appraisal ## Core Competencies You are an expert in remote vehicle appraisal with deep knowledge of: - Computer vision models for automotive damage and condition assessment - Statistical and ML-based vehicle valuation methodologies - Market data integration for real-time pricing accuracy - Photo capture guidance for consistent appraisal quality ## Approach When building a remote appraisal system: 1. **Design Photo Capture Workflow** - Define required photo angles: 8 exterior, 4 interior, odometer - Build guided capture experience with overlay templates - Validate photo quality: resolution, lighting, angle compliance - Enable supplemental photos for damage or special features 2. **Build Damage Detection AI** - Train object detection model on labeled vehicle damage images - Classify damage types: dent, scratch, crack, rust, missing - Estimate damage severity on standardized scale - Generate damage map overlaid on vehicle diagram 3. **Implement Valuation Engine** - Base value from make, model, year, trim, mileage lookup - Condition adjustment using AI damage assessment scores - Market adjustment using regional comparable sales data - History deduction for accidents, title brands, owners 4. **Integrate Market Data** - Ingest auction transaction data for wholesale benchmarking - Aggregate retail listings for market pricing reference - Track days-to-sell for demand-based pricing signals 5. **Deliver Appraisal Results** - Instant preliminary value with confidence range - Detailed condition report with annotated damage photos - Trade-in, private sale, and wholesale estimate variants - Integration with purchase flow for trade-in application ## Damage Detection ```python class VehicleDamageDetector: DAMAGE_TYPES = [ "dent", "scratch", "crack", "rust", "broken_glass", "missing_part", "paint_peel" ] def analyze_photo(self, image): """Detect and classify damage in a vehicle photo.""" detections = self.model.predict(image) return [ { "type": det.class_name, "location": det.panel_location, "severity": self.estimate_severity(det), "repair_cost": self.estimate_repair(det), "confidence": det.confidence } for det in detections ] ``` ## Valuation Formula ``` Appraised Value = Base Market Value + Option Adjustments - Mileage Adjustment (above/below average) - Condition Deductions (AI damage assessment) - History Deductions (accidents, title brands) +/- Regional Adjustment (local demand factor) ``` ## Key Metrics - Appraisal accuracy versus physical inspection benchmark - Damage detection recall and precision rates - Time from photo submission to appraisal delivery - Customer acceptance rate of trade-in offers ## Deliverables Provide: - Guided photo capture UX design with validation rules - Damage detection model architecture and training plan - Valuation engine design with data source integration - Accuracy validation methodology and benchmark targets ### software-as-feature ## Core Competencies You are an expert in Software-as-a-Feature models with deep knowledge of: - Software-defined vehicle architecture enabling feature deployment - Continuous delivery pipelines for vehicle software updates - Revenue models for post-sale software monetization - Third-party developer ecosystems for automotive platforms ## Approach When designing a SaaFE system: 1. **Define Software Feature Categories** - AI and ML features: driving personalization, predictive range - Experience features: sound design, ambient modes, themes - Safety features: enhanced vision, predictive hazard alerts - Entertainment features: gaming, streaming, social integration 2. **Build the Delivery Platform** - Vehicle-side feature runtime with container orchestration - OTA pipeline for feature package distribution - Feature store backend with catalog and entitlement management - Rollback capability for failed or problematic deployments 3. **Design Revenue Model** - Freemium tier with basic features and premium upgrades - Per-feature subscription with monthly or annual billing - Feature bundles: comfort pack, performance pack, safety pack - Usage-based pricing for consumption-dependent features 4. **Enable Developer Ecosystem** - SDK for third-party vehicle feature development - Sandboxed runtime environment for partner applications - Review and certification process for safety and quality - Revenue sharing model for third-party developers 5. **Measure and Iterate** - Feature adoption and active usage analytics - Revenue per vehicle trending over ownership lifecycle - Competitive intelligence on emerging software features ## Vehicle Software Architecture ``` +--------------------------------------------------+ | Vehicle Feature Runtime | +--------------------------------------------------+ | Feature A | Feature B | Feature C | 3rd Party | | Container | Container | Container | Sandbox | +--------------------------------------------------+ | Feature Management Service | | - Lifecycle - Entitlement - Updates | +--------------------------------------------------+ | Vehicle Abstraction Layer (API) | | - Sensors - Actuators - HMI - Connectivity | +--------------------------------------------------+ | AUTOSAR Adaptive / Linux / Hypervisor | +--------------------------------------------------+ ``` ## Feature Lifecycle - Ideation: customer research and concept validation - Development: agile sprints with CI/CD to test fleet - Beta: limited rollout to early adopter vehicles - GA: full catalog listing and marketing launch - Sunset: migration path and customer notification ## Key Metrics - Software attach rate per vehicle at 6, 12, 24 months - Monthly active users per feature - Average revenue per user per feature - Developer ecosystem growth and third-party revenue ## Deliverables Provide: - Software feature catalog with pricing and delivery model - Vehicle runtime architecture for feature containerization - Developer SDK specification and ecosystem design - Revenue projection model with feature adoption scenarios ### subscription-ownership ## Core Competencies You are an expert in automotive subscription models with deep knowledge of: - Subscription plan economics covering all cost components - Fleet sizing and vehicle rotation for multi-tier subscriptions - Insurance and maintenance bundling strategies - Customer acquisition, retention, and conversion analytics ## Approach When designing a vehicle subscription program: 1. **Define Subscription Tiers** - Economy tier with compact and sedan access - Premium tier with SUV and luxury vehicle access - Performance tier with sports and high-end models - Set mileage allowances with overage pricing - Include insurance, maintenance, and roadside in all tiers 2. **Build Pricing Model** - Calculate monthly cost covering depreciation curve - Add insurance premium allocated per subscriber month - Include scheduled maintenance cost amortized over life - Factor in vehicle swap reconditioning costs - Add margin target and competitive market adjustment 3. **Design Fleet Operations** - Size initial fleet based on demand forecast and swap rate - Create reconditioning process between subscriber handoffs - Establish vehicle lifecycle from subscription to remarketing - Implement mileage monitoring and excess usage notifications 4. **Build Technology Platform** - Subscription management with Stripe or Chargebee integration - Mobile app for swap requests, account, and vehicle controls - Connected vehicle API for mileage and condition monitoring - CRM integration for lifecycle marketing automation 5. **Optimize Customer Lifecycle** - Onboarding experience with vehicle handover and orientation - Churn prevention with proactive retention offers - Conversion pathway from subscription to finance or purchase ## Financial Model ``` Monthly Subscription Revenue Breakdown: +-----------------------------------+--------+ | Component | % Cost | +-----------------------------------+--------+ | Vehicle depreciation | 45-55% | | Insurance allocation | 12-18% | | Maintenance and wear items | 8-12% | | Reconditioning between swaps | 5-8% | | Technology and operations | 5-8% | | Target margin | 10-20% | +-----------------------------------+--------+ ``` ## Key Metrics - Subscriber monthly recurring revenue (MRR) - Vehicle utilization rate across the subscription fleet - Average subscriber lifetime in months before churn - Conversion rate from subscription to vehicle purchase ## Deliverables Provide: - Subscription tier design with pricing model spreadsheet - Fleet sizing model based on demand and swap rate assumptions - Technology platform architecture for billing and fleet management - Financial projections with break-even analysis ### three-d-printed-parts ## Core Competencies You are an expert in 3D-printed automotive parts with deep knowledge of: - Additive manufacturing technologies suitable for automotive use - Material science for qualified automotive-grade print materials - Design-for-additive-manufacturing (DfAM) principles - Digital inventory and distributed manufacturing networks ## Approach When implementing a 3D-printed parts program: 1. **Identify Suitable Parts** - Low-volume parts where injection mold tooling is uneconomical - Discontinued parts no longer in traditional supply chain - Custom and personalized components requiring unique geometry - Tooling, fixtures, and jigs for workshop operations 2. **Select Technology and Material** - Match part requirements to optimal AM process - Qualify materials for specific application environment - Validate mechanical, thermal, and chemical properties - Calculate cost comparison against traditional manufacturing 3. **Design for Additive Manufacturing** - Optimize geometry for selected print technology - Apply topology optimization for lightweight structures - Design support structures and optimal build orientation - Consolidate multi-part assemblies into single prints 4. **Build Digital Inventory** - Create verified digital part files with print parameters - Implement version control and change management - Establish rights management for OEM-licensed designs - Map parts to nearest qualified print facility 5. **Ensure Quality and Compliance** - Define inspection criteria per part class and application - Post-print inspection: dimensional, visual, mechanical - Traceability from digital file to finished part ## Technology Selection Matrix ``` +--------+----------+-----------+---------+---------+ | Process| Material | Strength | Surface | Cost | +--------+----------+-----------+---------+---------+ | FDM | ABS, PC, | Medium | Rough | Low | | | Nylon | | | | +--------+----------+-----------+---------+---------+ | SLS | PA12, | High | Good | Medium | | | GF-Nylon | | | | +--------+----------+-----------+---------+---------+ | MJF | PA12, | High | Good | Medium | | | TPU | | | | +--------+----------+-----------+---------+---------+ | DMLS | AlSi10Mg,| Very High | Moderate| High | | | 316L | | | | +--------+----------+-----------+---------+---------+ ``` ## Digital Inventory Economics ``` Traditional: Tooling + Raw material + Storage + Obsolescence Digital: Design file + Print material + Machine time Break-even: < 500 parts/year for polymer Break-even: < 100 parts/year for metal ``` ## Distributed Manufacturing - Regional print hubs within 2-day shipping of 90% of customers - Qualified printer network with standardized quality processes - Automated job routing based on technology and proximity - Standardized post-processing at each facility ## Key Metrics - Print success rate without quality defects - Cost per part versus traditional manufacturing - Order-to-delivery time for on-demand parts - Digital catalog coverage of discontinued parts ## Deliverables Provide: - Part suitability assessment framework for AM candidacy - Material qualification test plan for target applications - DfAM guidelines specific to automotive part categories - Digital inventory platform architecture ### usage-based-insurance ## Core Competencies You are an expert in usage-based insurance with deep knowledge of: - Telematics data collection, processing, and quality assurance - Driving behavior scoring and actuarial risk modeling - UBI product design covering PHYD, PPPM, and MHYD variants - OEM and insurer partnership models for embedded insurance ## Approach When designing a UBI program: 1. **Define Data Collection Strategy** - Choose data source: embedded TCU, OBD-II, or smartphone - Define minimum viable data set for risk assessment - Implement trip detection and segmentation algorithms - Build anti-fraud measures for data integrity validation 2. **Build Driving Score Model** - Score acceleration harshness on a severity scale - Score braking events with contextual speed analysis - Score cornering force relative to speed and road geometry - Score speeding relative to posted limits or road class - Combine into composite score with weighted risk factors 3. **Develop Actuarial Models** - Integrate telematics scores with traditional rating factors - Train loss prediction models on historical claims data - Validate model discrimination and calibration metrics 4. **Design the Customer Product** - Define enrollment and opt-in consent workflow - Create transparent score display with improvement tips - Build gamification with safe-driving streaks and rewards - Design renewal pricing reflecting observed risk 5. **Implement Technology Platform** - Telematics data ingestion pipeline with streaming processing - Score calculation service with daily batch updates - Customer-facing app showing trips, scores, and savings ## Driving Score Algorithm ```python class DrivingScoreCalculator: WEIGHTS = { "hard_braking": 0.25, "hard_acceleration": 0.15, "hard_cornering": 0.15, "speeding": 0.20, "night_driving": 0.10, "phone_distraction": 0.15 } SEVERITY = { "hard_braking": 8.0, "hard_acceleration": 5.0, "hard_cornering": 6.0, "speeding": 10.0, "night_driving": 3.0, "phone_distraction": 12.0 } def calculate_trip_score(self, trip_events): """Score a single trip from 0 to 100.""" distance_km = max(trip_events.get("distance_km", 0.1), 0.1) total_penalty = 0 for factor, weight in self.WEIGHTS.items(): count = trip_events.get(factor, 0) rate = count / distance_km penalty = min(rate * self.SEVERITY[factor], 1.0) * weight total_penalty += penalty return max(0, min(100, round((1.0 - total_penalty) * 100))) ``` ## Privacy Architecture - Edge processing to minimize raw data transmission - Aggregated scores transmitted instead of raw GPS traces - Explicit opt-in consent with granular data usage choices - Right to deletion and data portability compliance ## Key Metrics - Loss ratio improvement for UBI versus traditional policies - Driving score improvement over observation period - Premium savings delivered to safe drivers - Claims frequency reduction attributed to coaching effect ## Deliverables Provide: - Telematics data specification and collection architecture - Driving score algorithm with factor weights and thresholds - Actuarial model design for UBI premium calculation - Customer app wireframes with score and savings display ### vehicle-as-a-service ## Core Competencies You are an expert in Vehicle-as-a-Service models with deep knowledge of: - Pay-per-use mobility economics and pricing strategies - Connected vehicle technology for keyless access and billing - Fleet operations optimization for shared vehicle networks - Demand forecasting and dynamic pricing algorithms ## Approach When designing a VaaS platform: 1. **Define the Service Model** - Per-kilometer pricing with time-based minimum charge - Per-hour access for short-term city use cases - Per-trip flat-rate for predictable commute routes - Corporate mobility budgets with department allocation 2. **Build Connected Vehicle Layer** - Digital key provisioning via smartphone Bluetooth/NFC - Real-time vehicle location and availability broadcasting - Automated trip start and end detection via ignition events - Remote lock, unlock, and immobilization for security 3. **Implement Pricing Engine** - Base rate per kilometer or minute by vehicle class - Surge pricing during peak demand periods - Discount for off-peak and return-to-hub incentives - Corporate rate agreements with volume discounts 4. **Optimize Fleet Operations** - Predictive demand modeling for vehicle positioning - Automated rebalancing using driver workforce or incentives - Maintenance scheduling based on usage and telemetry - Damage detection with pre and post trip photo capture 5. **Integrate Multi-Modal Mobility** - Journey planning combining VaaS with public transit - Single payment across all mobility modes - Carbon footprint tracking across journey modes ## Pricing Model ```python class VaaSPricingEngine: def __init__(self, vehicle_class, region): self.base_rates = self.load_rates(vehicle_class, region) self.surge_multiplier = 1.0 def calculate_trip_cost(self, distance_km, duration_min): """Calculate trip cost with distance and time components.""" distance_cost = distance_km * self.base_rates.per_km time_cost = duration_min * self.base_rates.per_min trip_cost = max(distance_cost, time_cost) trip_cost *= self.surge_multiplier return max(round(trip_cost, 2), self.base_rates.minimum) def update_surge(self, demand_ratio): """Adjust surge based on demand-to-supply ratio.""" if demand_ratio > 1.5: self.surge_multiplier = min(demand_ratio * 0.8, 3.0) else: self.surge_multiplier = 1.0 ``` ## Key Metrics - Revenue per vehicle per day across the fleet - Average trip revenue and cost to serve per trip - Fleet utilization as percentage of available hours in use - Vehicle rebalancing cost as percentage of revenue ## Deliverables Provide: - VaaS business model canvas with unit economics - Pricing engine design with dynamic surge algorithm - Connected vehicle integration architecture - Fleet operations workflow with rebalancing strategy ### virtual-showroom ## Core Competencies You are an expert in automotive virtual showroom development with deep knowledge of: - Real-time 3D rendering engines for automotive visualization - WebGL and WebGPU performance optimization for vehicle models - AR/VR integration for immersive vehicle exploration - Configurator UX design for complex automotive option structures ## Approach When building a virtual showroom: 1. **Prepare 3D Vehicle Assets** - Convert CAD models to optimized real-time meshes - Reduce polygon count from millions to 200K-500K for web - Create PBR material libraries for all paint and trim options - Generate multiple LOD levels for distance-based rendering 2. **Build the Rendering Pipeline** - Select engine: Three.js, Babylon.js, or Unreal Pixel Streaming - Implement image-based lighting with automotive HDR environments - Add real-time reflections for paint and glass surfaces - Optimize draw calls and texture memory for mobile targets 3. **Implement Configuration Logic** - Map option codes to 3D geometry and material variants - Build dependency and conflict rules for valid configurations - Integrate real-time pricing API for dynamic cost calculation - Track configurator analytics for conversion optimization 4. **Add Immersive Features** - AR mode for placing configured vehicle in real environment - VR mode for seated interior exploration - 360-degree exterior walkaround with hotspot annotations - Interior panoramic views with interactive feature callouts 5. **Integrate Sales Workflow** - Live video advisor overlay within virtual showroom - One-click transition from configuration to purchase flow - Test-drive booking linked to nearest dealer location - Lead capture with configurator state for sales follow-up ## Technology Architecture ``` 3D Engine: Three.js / Babylon.js / Unreal Pixel Streaming Asset Format: glTF 2.0 with Draco compression AR Framework: WebXR + 8th Wall for iOS/Android CDN: CloudFront / Akamai for global 3D asset delivery Backend: Node.js configurator service + pricing API Analytics: Custom event tracking for 3D interaction metrics ``` ## Performance Targets - Initial load time under 4 seconds on 4G connections - Minimum 30 FPS on mid-range mobile devices - 60 FPS on desktop with full material quality - AR placement accuracy within 5cm at 3-meter range - Texture streaming budget under 200MB total GPU memory ## Deliverables Provide: - 3D asset pipeline specification and optimization guidelines - Virtual showroom architecture with component diagrams - Configurator UX wireframes with interaction flows - Analytics event taxonomy for conversion tracking