SnobBots · Ecommerce / Customer support
Multi-tenant AI chatbot platform.
Category
AI
Year
2023-2024
Capabilities
AI, Cloud & Automation
Industry
Ecommerce / Customer support
The problem
Resellers wanted to offer AI support agents to their own customers, but every deployment was bespoke, so onboarding a new shop took days of manual setup.
Our approach
We built a multi-tenant MERN architecture where each shop runs an independent, context-aware agent, and layered automated provisioning on top so resellers could stand up bots in bulk rather than one at a time.
Inside the product
More than one screen.
3 more screens from SnobBots, captured at device size.
Handover inbox
Conversations the bot could not close, with the order and customer beside them.
Knowledge base
The catalogue, orders API and policies each bot is allowed to answer from.
Shop widget
The customer-facing chat as it appears on a client’s storefront.
On the phone
Home
Handover inbox
Knowledge base
Shop widget
How it is built
Architecture
MERN: React, an Express and Node.js API, and MongoDB for tenant and conversation data. Pinecone holds per-tenant embeddings so retrieval is scoped to one shop’s knowledge base, and provisioning runs without manual setup.
Key features
Challenges & solutions
Challenge
Retrieval across a shared vector index surfaced one shop’s content in another shop’s answers.
Solution
Partitioned embeddings per tenant in Pinecone so retrieval can only ever reach the requesting shop’s namespace.
Challenge
Manual per-shop setup made reseller onboarding the bottleneck on growth.
Solution
Automated provisioning end to end, turning a multi-day manual process into a bulk operation.
Results
What shipping it changed.
Resellers now stand up AI support agents for their shops in bulk instead of one bespoke deployment at a time. Each bot answers only from its own shop’s catalogue, orders and policies, and hands over to a person when it cannot close a conversation.
60%
faster shop onboarding
Automated provisioning turned a multi-day manual setup into a bulk operation.
1
isolated namespace per shop
Embeddings are partitioned per tenant in Pinecone, so no bot can ever surface another shop’s content.
100%
of answers grounded in the shop’s own content
Retrieval runs over the catalogue, orders API and policies the reseller has allowed for that bot.
Stack
Frontend
- React
Backend
- Node.js
- Express
Database
- MongoDB
- Pinecone
AI
- RAG
- LLM
Let's talk
We can usually tell within one call whether the approach above transfers to your problem, and what would need to change.