Product Requirements
Plock PRD, AI features, integrations (Fortnox, PostNord, DHL, Shopify), user personas

AI Features (Priority Order)
AI Features (Priority Order) 
 Overview 
 Plock is AI-native — not AI-bolted-on. Every data model is designed with AI querying in mind. The AI layer runs continuously; warehouse workers are alerted, not asked to check. 
 Target user for AI: A warehouse worker with dirty gloves asking var finns SKU-X on a cracked phone screen — not an analyst building pivot tables. 
 Language: Swedish first. Short, direct responses. Action-oriented. Mobile-friendly. 
 
 Priority 1 — Plock AI Chat (Launch) 
 Type: LLM natural language interface
 Model: Claude API (claude-sonnet-4-5)
 Language: Swedish 
 What it does 
 
 Answer warehouse questions in natural language Swedish 
 Execute actions with single confirmation (move stock, reserve, assign pick) 
 Access real-time inventory, orders, performance data 
 Multi-turn conversation with warehouse context injected 
 
 Example queries 
 
 Hur manga enheter av SKU-1234 har vi? — live stock count + trend 
 Vilka ordrar ar forsenade idag? — list with root cause 
 Flytta 50 enheter fran A-01-01 till B-02-03 — confirmation + action 
 
 Architecture 
 
 System prompt includes: warehouse schema snapshot, org context, user role, current time 
 Function calling for write operations (move, reserve, assign) 
 Organization data never sent raw to Claude — only sanitised context 
 Response target: less than 3 seconds 
 
 
 Priority 2 — Smart Picking (Launch) 
 Type: Route optimisation
 Engine: OR-Tools (Google) — VRP/TSP solver
 Reduction target: 30-70% travel time 
 What it does 
 
 Automatically generates optimal pick routes when orders are released 
 Groups orders into picking waves based on zone, carrier cutoff, priority 
 Outputs sequential bin list on mobile scanner 
 No configuration required — runs on every order release 
 
 How it works 
 
 Order released — ML microservice receives order + bin locations 
 OR-Tools VRP solver computes shortest path across warehouse zones 
 Optimised pick list returned to mobile app in under 2 seconds 
 Worker follows sequence — no backtracking 
 
 ROI 
 
 Industry data: 30-70% of warehouse time is walking (not picking) 
 Conservative 20% efficiency gain = 8,800 SEK/month per worker saved 
 
 
 Priority 3 — Anomaly Detection (Launch) 
 Type: Statistical detection on inventory transactions
 Algorithms: Z-score + isolation forest (scikit-learn)
 Trigger: Real-time, on every transaction 
 What it detects 
 
 Sudden stock drops (theft, mispick, data error) 
 Unusual pick rates (demand spike or data entry error) 
 Inventory discrepancy after goods receipt 
 Carrier label printed but no scan out (lost shipment risk) 
 
 Alert flow 
 
 Transaction recorded — Python microservice analyses against rolling baseline 
 Z-score above 3 sigma or isolation forest flags as outlier — alert created 
 Warehouse manager receives push notification + AI chat message 
 Manager confirms or dismisses — feedback improves model 
 
 
 Priority 4 — Demand Forecasting (Month 6) 
 Type: Time-series forecasting
 Models: XGBoost + Prophet (Facebook)
 Input: Order history (minimum 90 days) 
 What it does 
 
 Predicts demand per SKU for next 7/14/30 days 
 Generates reorder recommendations with suggested quantity and timing 
 Adjusts for seasonality (Swedish calendar events, e-commerce peaks) 
 Accessible in AI Chat: Vad ska vi bestalla hem nasta vecka? 
 
 
 Priority 5 — Smart Slotting (Month 6) 
 Type: ML-based placement recommendations
 Input: Pick frequency, order affinity, SKU dimensions 
 What it does 
 
 Recommends optimal bin locations for each SKU based on pick frequency 
 Groups frequently co-picked SKUs near each other (affinity slotting) 
 Identifies slow-movers in prime locations and suggests moves 
 Presented as actionable task list, not a forced migration 
 
 
 Priority 6 — Labor Planning (Month 12) 
 Type: Shift optimisation
 Constraints: Swedish labour law (Arbetstidslagen) 
 What it does 
 
 Predicts staffing needs based on demand forecasts 
 Generates compliant shift schedules (max hours, breaks, rest periods) 
 Suggests overtime or temp worker needs 1-2 weeks in advance 
 Integrates with order volume forecasts from Demand Forecasting module 
 
 
 AI Cost Model (per customer) 
 
 
 
 Feature 
 Est. cost/month (Growth plan) 
 
 
 
 
 Plock AI Chat (1,000 queries/month) 
 ~45 SEK (Claude Sonnet pricing) 
 
 
 Smart Picking (10,000 optimisations) 
 ~5 SEK (OR-Tools compute) 
 
 
 Anomaly Detection (100K transactions) 
 ~10 SEK (Python microservice) 
 
 
 Total AI cost per Growth customer 
 ~60 SEK/month 
 
 
 Growth plan revenue 
 2,990 SEK/month 
 
 
 AI cost as % of revenue 
 ~2%

Key Integrations
Key Integrations 
 Integration Priority Table 
 
 
 
 Integration 
 Type 
 Priority 
 Launch Date 
 
 
 
 
 Fortnox 
 REST v3, OAuth2 
 P0 
 Launch 
 
 
 PostNord 
 REST, OAuth2 
 P0 
 Launch 
 
 
 DHL Sweden 
 REST 
 P1 
 Month 2 
 
 
 Instabee / Budbee 
 REST JSON 
 P1 
 Month 3 
 
 
 Shopify 
 REST + GraphQL 
 P1 
 Month 3 
 
 
 WooCommerce 
 REST 
 P2 
 Month 6 
 
 
 Visma 
 REST 
 P2 
 Month 6 
 
 
 
 
 P0 — Fortnox (Launch Critical) 
 Why P0: 598,000 Swedish companies use Fortnox. Fortnox Marketplace is the primary distribution channel. Deep integration = instant value for every new customer. 
 API: Fortnox REST API v3 (api.fortnox.se)
 Auth: OAuth2 (authorisation code flow) 
 Sync scope 
 
 
 
 Data 
 Direction 
 Frequency 
 
 
 
 
 Products (artiklar) 
 Fortnox to Plock 
 On demand + webhook 
 
 
 Suppliers (leverantorer) 
 Fortnox to Plock 
 On demand 
 
 
 Purchase orders 
 Bidirectional 
 Real-time 
 
 
 Sales orders 
 Fortnox to Plock 
 Real-time (webhook) 
 
 
 Stock levels 
 Plock to Fortnox 
 On every transaction 
 
 
 Invoices 
 Plock to Fortnox 
 On order completion 
 
 
 
 Fortnox Marketplace listing 
 
 Plock listed as official Fortnox Marketplace integration 
 Customers connect via OAuth flow directly from Fortnox UI 
 Integration reviewed and certified by Fortnox team 
 
 
 P0 — PostNord (Launch Critical) 
 Why P0: PostNord is the dominant carrier for Swedish e-commerce (primary for ~70% of SMBs). 
 API: PostNord REST API (developer.postnord.com)
 Auth: OAuth2 
 Features 
 
 Generate shipping labels (PDF + ZPL for Zebra printers) 
 Book pickup 
 Track shipments (webhook updates) 
 Print manifests at end of day 
 Support for: PostNord MyPack, Varubrev, DHL Parcel (via PostNord reseller) 
 
 
 P1 — DHL Sweden (Month 2) 
 API: DHL Express REST (developer.dhl.com)
 Features: Label generation, booking, tracking, rate quotes
 Auth: API key 
 
 P1 — Instabee / Budbee (Month 3) 
 API: Instabee REST JSON (developer.budbee.com)
 Features: Label generation, booking, real-time tracking, consumer notifications
 Note: Instabee acquired Budbee — same API, two brands 
 
 P1 — Shopify (Month 3) 
 API: Shopify REST Admin API + GraphQL
 Auth: OAuth2 (Shopify Partner app) 
 Sync scope 
 
 Orders to Plock outbound queue 
 Inventory levels bidirectional (Plock as source of truth) 
 Product catalogue to Plock (read-only) 
 Fulfilment events to Shopify order tracking 
 
 
 P2 — WooCommerce (Month 6) 
 API: WooCommerce REST API
 Auth: API key
 Sync scope: Orders, products, inventory levels (similar to Shopify) 
 
 P2 — Visma (Month 6) 
 API: Visma eAccounting REST API
 Auth: OAuth2
 Sync scope: Similar to Fortnox — products, orders, invoices, stock levels 
 
 Integration Architecture 
 All integrations run through the Integration Layer in the Kotlin backend: 
 File structure: 
 
 integrations/fortnox/ — FortnoxClient.kt, FortnoxSyncService.kt, FortnoxWebhookHandler.kt 
 integrations/carriers/ — PostNordClient.kt, DhlClient.kt, InstabeeClient.kt 
 integrations/ecommerce/ — ShopifyClient.kt, WooCommerceClient.kt 
 
 Queue: Redis + Kotlin coroutines for async integration jobs (label generation, carrier calls, sync tasks) 
 Error handling: Retry with exponential backoff, dead-letter queue, alert on persistent failure