S&B Filters: From Prototype to Production AI in 4 Weeks

0%

of support
fully automated

<0

weeks to
production

0x

faster first
response

0%

ROI in
Year 1

About the Client

S&B Filters is a U.S.-based manufacturer of high-performance air filters for the automotive aftermarket. With 700+ employees and a complex, multi-channel business, the company runs its core operations — order management, internal workflows, customer data — on NetSuite.

Industry

Manufacturing & Distribution

Channels

Website, Shopify, Phone

Use case

AI Transformation, NetSuite Integration, Customer Support Automation

Technology

OpenAI, Java Spring Boot, Pinecone, React, AWS

As the business scaled, so did the volume of customer inquiries — especially around order status, delivery timelines, and product details — putting increasing pressure on the support team.

The company attempted to solve this with AI — but the results fell short.

The Challenge

S&B's CEO, Berry Carter, is the kind of leader who builds before he buys. Rather than wait for a vendor pitch, he wired up Claude's MCP (Model Context Protocol) connector to NetSuite himself, wrote his own prompts, and stood up an internal AI assistant for order status.

For a CEO-built prototype, it worked. It proved the use case. It showed the team what was possible.

Then the limitations of an experiment-grade architecture surfaced:

4–6 min

Response times

Responses took 4–6 minutes — too slow for real customer interactions.

40 pages

Prompt architecture

A 40-page prompt made the system hard to maintain, control, and keep consistent.

3+ formats

Data variability

PO numbers arrived in different formats across Shopify, phone, and email orders.

No path

To production

Behaved as an internal tool, not a customer-grade system.

The Solution: A Production AI Layer Purpose-Built for NetSuite

We didn't extend the prototype. We rebuilt the architecture from the ground up — a custom AI agent stack engineered for S&B's data, channels, and operational realities.

The result is not a chatbot. It's an AI layer on top of NetSuite that serves internal teams and external customers from a single foundation.

📦 AI for a High-Impact Use Case — Order Status (Powered by NetSuite)

We started with what delivers the most immediate value: instant access to NetSuite data and order status. The AI assistant now:

integrates directly with ERP (NetSuite)
retrieves order data instantly
works across Shopify and phone orders
handles both structured and highly unstructured inputs.

🖥️ Two Interfaces — One NetSuite AI Layer

To maximize impact, we deployed the solution across two key environments:

1. Internal AI Assistant (for support teams)

The most critical use case for operations:

agents can instantly retrieve order data by simply entering an order or PO number
eliminates manual navigation across NetSuite
significantly reduces handling time and cognitive load

👉 What used to take minutes inside NetSuite now takes seconds.

2. Customer-Facing AI Assistant (website)

A self-service layer for end users:

instant order status updates
reduced need to contact support
24/7 availability.

🧠 AI as a Product Expert (Knowledge Base Layer)

We extended AI beyond transactions into product knowledge. The assistant now:

answers installation and compatibility questions
supports technical inquiries
enriches responses with images, videos, and step-by-step guides.

This complements NetSuite by bridging the gap between data and customer understanding.

Previously, agents had to manually navigate the NetSuite interface to locate order details — a time-consuming and fragmented process. With the AI assistant, they can now simply enter an order or PO number and instantly retrieve all relevant information.

What used to take minutes of manual search is now reduced to seconds — significantly improving both response speed and agent efficiency.

Key Features

Deep NetSuite Integration

Real-time access to orders, customers, and operational data.

Instant Order Tracking

Live status including backorders and manufacturing dates.

AI Product Expert

Step-by-step guides, images, and technical instructions.

Part Availability & Production Insights

Part stock levels and upcoming production schedules.

Dynamic Knowledge Base

Always up-to-date via OneDrive with role-based access.

Coming Soon

Full Order Control

Place, modify, or cancel orders — and much more!

What Made It Work

1. Making NetSuite Data Usable for AI

NetSuite is structured. Real-world inputs are not. We built a layer above the ERP that:

Validates inputs across formats and data sources
Falls back across identifiers (Sales Order → PO number → customer reference)
Uses conversation context to infer intent

👉 This allows the system to consistently deliver accurate results — even when inputs vary across channels.

2. Extending NetSuite with a Dynamic Knowledge Layer

Product knowledge is continuously evolving — with new products, updated installation guides, and varying levels of access requirements. While NetSuite provides a robust foundation, enabling this level of flexibility and content control benefits from an additional, purpose-built layer.

We built a dynamic knowledge layer connected to — but not limited — NetSuite:

OneDrive integration for easy content updates by the client
structured document formats optimized for AI processing
controlled visibility rules to separate internal vs customer-facing data
instant updates without system redeployment.

👉 The AI always delivers accurate, up-to-date answers — without exposing sensitive internal information.

3. Speed as a Core Metric

The previous solution technically worked — but with 4–6 minute response times, it was unusable in real workflows. Support agents still had to manually search NetSuite, and customers experienced delays.

We optimized for instant access to NetSuite data, not just answer quality:

fast, direct data retrieval from ERP
minimal latency in AI responses
real-time interaction design

👉 What used to take minutes now takes seconds — enabling both faster support and a seamless customer experience.

Technologies Used

AI Layer

OpenAI API

Pinecone

Backend

Java Spring Boot

Frontend

React

Redux

React Router

DevOps

Docker

GitHub Actions

AWS ECR

Projected Business Impact

For S&B Filters, this is no longer a support project. It's the foundation for an AI-first operation:

AI is embedded in core workflows, not bolted on the side
A single architecture serves both internal teams and external customers
The same platform is already extending into orders, invoices, dealer identification, and personalized discounts

For other companies running on NetSuite, S&B is a reference point. The same approach — production AI layered on top of the ERP — applies across operations, finance, support, and sales.

$140K

annual cost savings

~50%

of requests fully automated

24x

faster first response time

~250%

ROI in Year 1

*Methodology note: Estimates are based on pre-implementation ticket volume, average handling time reduction driven by AI-assisted responses, and typical support agent cost benchmarks. Automation rate reflects the share of inquiries fully resolved by AI without human intervention, while ROI accounts for both operational savings and implementation costs.

"The initial solution I built was slower than I needed it to be, simply because I wrote it. So we hired BotsCrew because we wanted to speed it up dramatically. They came in and did exactly that — we now get all that information in 15 seconds for our techs, which is just phenomenal. But they also took it to the consumer level: we deployed it as an agent on our website, so consumers now get that exact same information on a secure basis. It has transformed our business, given us a lot of information very quickly, and really helped us handle our backorders."

Berry Carter

S&B Filters, CEO

What's Next

Already on the roadmap:

Full order control — customers placing, modifying, and canceling orders via the assistant
Dealer identification via NetSuite data
Personalized discounts based on customer history
Invoice access through the chatbot
Deeper Zendesk automation

Ready to cross your own AI gap?

If your team has already proven the concept with a Claude prototype, an MCP connector, or an internal AI experiment — and you're trying to figure out what it takes to make it operational — that's the conversation we have most often.

Book a Free AI Consultation