# A company’s own documents, answering its customers, with sources.

> Qualihelp is a multi-tenant branded AI SaaS. A company embeds an assistant on its own site with one script tag, uploads its documents, tests retrieval, and publishes answers with citations. We built the platform, the widget and the admin portal.

- URL: https://bon.do/en/work/qualihelp
- Client: Qualihelp
- Sector: AI and customer service
- Platforms: Web widget, tenant portal and admin portal
- Role: Full build
- Outcome: Tenants publish a cited AI assistant on their own site, without a developer.
- Tags: SaaS, Automation

## Overview

Qualihelp is a multi-tenant branded AI SaaS. A company embeds an assistant on its own site with one script tag, uploads its documents, tests retrieval, and publishes answers with citations. We built the platform, the widget and the admin portal.

A branded AI assistant is only useful if it answers from the company’s own material, cites the source, and does not invent. The platform also has to meter AI cost per tenant, route documents to the right corpus or skill, and let a tenant publish a new version without a developer.

We built a multi-tenant branded AI SaaS with an ASP.NET Core API, Wolverine, PostgreSQL, S3 and NATS JetStream. The worker extracts text and images, describes them, chunks and embeds documents into a draft corpus version, and the tenant activates a version after testing retrieval in the playground. The widget streams answers over SSE with citations. Every AI call runs inside a per-tenant metering scope.

A tenant can upload a document, test retrieval and publish a cited assistant on its own site without a developer. The platform tracks AI cost, usage and queue health per tenant, and operators can control which model each tenant may use.

## Results

- **One platform:** 3 surfaces. Widget, tenant portal and admin portal.
- **To embed:** 1 tag. One script tag on the customer’s site.
- **Streaming:** SSE. Cited answers, streamed as they are generated.

## At a glance

- **Client:** Qualihelp
- **Product:** Branded AI assistant
- **Users:** Tenants · their customers · platform support
- **Our role:** Full build
- **Type:** B2B SaaS
- **Stack:** ASP.NET Core · Wolverine · PostgreSQL · S3 · NATS · Angular
- **Timeline:** Ongoing product partnership

## What we built

### 01. Ingestion

Text and images extracted, described, chunked and embedded into a draft corpus version.

### 02. Retrieval

Hybrid RAG with citations, a retrieval playground and an activation step before anything goes live.

### 03. Operations

Per-tenant metering, AI cost, queue health and model control.

## How it ran

### 01. Discover: Answers that hold

What a good answer looks like, and what the assistant must refuse.

### 02. Design: A playground for truth

Retrieval, citations and the activation step designed for a non-technical tenant.

### 03. Build: Ingest, retrieve, meter

A worker, an API and a widget built as one metered system.

### 04. Run: Cost under control

Per-tenant cost, usage and queue health from day one.



## Contact

Bon.do ApS · Rantzausmindevej 228, 5700 Svendborg, Denmark · info@bon.do · https://bon.do/en/contact-us