Working Prototype2025
Pasukhi
Multi-tenant AI messaging automation across Instagram, Facebook & WhatsApp.
Summary
Multi-tenant SaaS that auto-responds to customer DMs across Instagram, Facebook and WhatsApp using AI-generated replies — tenant-isolated, queue-backed, horizontally scalable.
Problem
Small businesses get DMs across three Meta channels at all hours. Manual replies don't scale; off-the-shelf bots don't know the business. Each tenant needs its own bot personality and data, fully isolated from every other tenant.
Approach
- 01Built on ASP.NET Core 8 with a clean multi-tenant architecture — each tenant's data and bot configuration fully isolated.
- 02Integrated RabbitMQ as a message broker to handle high-throughput inbound webhook events from Meta APIs asynchronously and reliably.
- 03Persisted tenant configurations, conversation history, and message queues in PostgreSQL via EF Core.
- 04Decoupled ingestion, processing, and delivery layers to support future horizontal scaling.
Highlights
- Multi-tenant data & bot isolation
- RabbitMQ-backed async ingestion
- Three-channel Meta integration (IG / FB / WA)
- Decoupled ingest → process → deliver pipeline
Stack
ASP.NET Core 8PostgreSQLEF CoreRabbitMQMulti-tenantMeta Graph APIsAI / LLM