Banya LabsBanya Labs/Apps/SchoolShop - Preloved & Uniform Storefront
In progress

App 03  ·  FIG. 003

SchoolShop - Preloved & Uniform Storefront logo

SchoolShop - Preloved & Uniform Storefront

Automated WhatsApp uniform store & lost property marketplace for schools

E-CommerceEdTechWhatsApp
App not yet live

Customer Target

South African Creches, Primary Schools, High Schools, Principals, Uniform Shops & Parents

Status

In progress

Agent Surface B

MCP Ready

Model Context Protocol Enabled

Registered in /.well-known/mcp.json & /llms.txt with deterministic Zod schema validation.

About Product

Full-stack multi-tenant uniform store and lost & found management system built with Next.js 15, Tailwind CSS, and Evolution API WhatsApp Gateway integration.

Key Features & System Mechanics: • Multi-Tenant School Isolation: Supports multiple school campuses with custom ZAR banking credentials, school crest branding, and dedicated WhatsApp channels. • Parent Storefront: Real-time inventory browsing with multi-size selection, live stock quantity tracking, category filters, and modal cart checkout. • Automated WhatsApp Engine: Frictionless OTP phone verification, automated EFT payment instruction dispatch, and instant office pickup notification alerts. • Bursar & Admin Panel: Order fulfillment dashboard, stock quantity manager with inline adjustment controls, lost & found auto-cataloguing, and live dispatch logs.

Dual-Surface Execution

Human vs. Agent Flow

Every action in SchoolShop - Preloved & Uniform Storefront is mapped bi-directionally across Surface A (Visual UI) and Surface B (Programmatic MCP Engine).

Surface A — Human Ergonomics Flow
  1. 01School lists official stock & unclaimed lost property items with available sizes and stock levels.
  2. 02Parent verifies identity via WhatsApp OTP, chooses uniform items and sizes, and submits order.
  3. 03Evolution API engine automatically sends school EFT banking details and order code to parent's WhatsApp.
  4. 04Bursar verifies Proof of Payment (POP) in the admin desk and triggers an automated pickup WhatsApp alert.
Surface B — Agentic Machine Execution Rails
Protocol: Model Context Protocol (MCP 1.0)Auth: Bearer banya_ag_...

1. Discovery: Scraper/Agent fetches /llms.txt or /.well-known/mcp.json manifest.

2. Tool Invocation: Executes deterministic Zod-validated tool contracts matching schoolshop-preloved operations.

3. Replay Protection: Enforces Idempotency-Key: <uuid> to prevent duplicate mutations during LLM retry loops.

4. Token Compression: Returns structured, PII-minimized Markdown/JSON stripping all layout noise.