Bud Case Study
Bud × FoundationFlow × Intel · RAG Customer Support

Driving enterprise RAG innovation on Intel Xeon

Bud Ecosystem, FoundationFlow, and Intel built a custom Retrieval-Augmented Generation chatbot for product-catalogue support — running on Intel® Xeon® processors with the BudServe engine. It delivers GPU-comparable performance on CPU, with roughly 60% better catalogue-query handling.

~60%
Better catalogue handling
124.89
Avg transactions/sec
100+
Concurrent users
48-core
Single Xeon server
Prepared byBud Ecosystem Inc.
PartnersFoundationFlow · Intel
PlatformIntel® Xeon® · BudServe engine
DateNovember 2024
Driving Enterprise RAG Innovation with Intel® Xeon® Bud
Overview

Customer support, rebuilt on retrieval.

Customer support is increasingly challenged to meet rising expectations for quick, accurate, and personalised responses — particularly with complex product queries. Bud Ecosystem, FoundationFlow, and Intel developed an advanced RAG-based chatbot, powered by Intel® Xeon® processors, to enhance accuracy and efficiency in handling product-catalogue inquiries.

The solution integrates external knowledge sources, provides direct access to product information, and adds improved table-parsing capabilities — with the BudServe engine leveraging Intel® Xeon® processors for superior performance.

Where traditional RAG falls short

  • Limited contextual understanding. Traditional RAG systems struggle to grasp the broader context of a query — even when relevant documents are retrieved, answers can be irrelevant or incomplete.
  • Slow response times. Slow token generation and processing delays create long wait times that frustrate customers and erode their perception of support quality.
  • Poor table comprehension. Many queries involve product specs presented in tables; legacy systems often fail to parse tabular data, producing inaccurate or incomplete responses.
The opportunity

Together these limitations hinder the effectiveness and efficiency of traditional RAG chatbots — and open the door to a custom, Intel-optimised approach.

Bud Ecosystem · Case Study02
Driving Enterprise RAG Innovation with Intel® Xeon® Bud
The Solution

A custom RAG, tuned for Intel.

The partners built a custom RAG solution to enhance context understanding, improve response times and accuracy, and create a more efficient support system. Leveraging FoundationFlow’s Co-pilot Builder module and Intel® Xeon® processors, the chatbot integrates seamlessly with external knowledge sources for precise, informative answers.

1

Direct product-catalogue access

The system bypasses manual data entry and separate database integrations by directly accessing extensive product catalogues and documents — so the chatbot always has up-to-date specifications and details.

2

Enhanced table parsing

Advanced parsing and interpretation of tables within product catalogues lets the chatbot accurately address complex queries about features and configurations — overcoming a key limitation of traditional LLM systems.

3

Optimization for Intel architecture

Fine-tuned for Intel® Xeon® processors, the RAG system leverages their high-performance processing and scalability for fast responses and smooth operation — even at high inquiry volume — while keeping infrastructure costs efficient.

Bud Ecosystem · Case Study03
Driving Enterprise RAG Innovation with Intel® Xeon® Bud
The Engine

BudServe on Intel Xeon.

Bud Ecosystem’s proprietary inference engine significantly boosts the performance of the overall stack — delivering faster response times and superior performance even under high user loads. It supports less-compute devices while providing performance comparable to GPU solutions.

100+
Concurrent users supported
48-core
Single server, no degradation
125 t/s
Avg token generation
≈ GPU
Performance, on CPU
Application
RAG customer-support chatbot
Built with FoundationFlow’s Co-pilot Builder, wired to live product catalogues.
Inference engine
BudServe
Bud’s proprietary engine — high concurrency and efficient token generation, GPU-comparable on CPU.
High concurrency125 tok/sCPU-first
Hardware
Intel® Xeon® processors
A single 48-core server sustains 100+ concurrent users without noticeable degradation.
Figure 1. The RAG stack — FoundationFlow’s Co-pilot Builder over the BudServe engine, running on Intel® Xeon® processors.

The architecture is optimised for high concurrency, ensuring smooth operation even during peak usage, and produces an average output of 125 tokens per second — delivering faster responses and a more responsive support experience.

Bud Ecosystem · Case Study04
Driving Enterprise RAG Innovation with Intel® Xeon® Bud
The Evidence

Key Results

Superior performance versus leading cloud chatbots — with measurable gains in catalogue handling, throughput, and support quality.

Driving Enterprise RAG Innovation with Intel® Xeon® Bud
Key Results

Outperforming cloud chatbots.

The chatbot solution demonstrated superior performance compared to leading cloud-based solutions — including Google Gemini Advanced, ChatGPT Plus, and Perplexity.

~60%
Better catalogue-query handling
124.89
Avg transactions/sec (TPS)
100+
Concurrent users
3
Cloud chatbots outperformed
Performance improvement

A nearly 60% improvement in handling product-catalogue queries, and an average of 124.89 transactions per second — high efficiency and speed across a large volume of transactions.

Impact on customer support

  • Efficiency and accuracy. The RAG approach significantly improved the chatbot’s ability to retrieve and generate accurate responses from a vast information repository.
  • Direct catalogue access. Pulling the most current, comprehensive product information directly from the catalogue sped up responses and ensured accuracy.
  • Enhanced table parsing. Improved parsing of tabular data let the chatbot handle complex queries involving detailed specifications more effectively.
Bottom line

Together these enhancements streamline customer-support operations — reducing customer frustration and improving the overall experience, with a scalable, cost-efficient approach that runs on infrastructure enterprises already own.

Bud Ecosystem · Case Study05