Small service businesses like fitness studios and salons juggle bookings across messaging apps, calendars, and payment links. As volume increases, missed messages, double bookings, and manual follow-ups become the norm.

Customers want to book the way they already communicate - through WhatsApp. But building a conversational booking experience that handles natural language, manages capacity in real-time, and prevents race conditions is a complex engineering challenge.

We built a WhatsApp-first booking experience where customers book using natural language like "I want yoga tomorrow at 7pm". The AI layer implements the MCP (Model Context Protocol) with a ports and adapters architecture - making the system LLM-agnostic and able to integrate any language model. Custom tools handle session discovery, booking management, staff info, and business operations.

The NestJS backend uses MongoDB with atomic operations to ensure race-condition safe bookings. Real-time capacity management includes waitlist support with automatic promotion when spots open up. The multi-tenant architecture supports multiple businesses with complete data isolation.

• - 285+ passing tests with 85% code coverage across unit, integration, and E2E tests.
• - <3s end-to-end response time from WhatsApp message to booking confirmation.
• - Race-condition safe: 50 parallel booking requests on a 10-capacity session → exactly 10 succeed.
• - <50ms p95 latency for session queries and booking operations.
• - Multi-tenant architecture supporting multiple businesses with complete data isolation.