How One Manufacturer Halved RFQ Turnaround

A 70-year-old manufacturer's engineers re-keyed RFQs across legacy systems. A Claude Code workbench now matches 40,000 SKUs and drafts the bill of materials — halving turnaround.

3.5 weeks

Built and deployed in 3.5 weeks

6–12 months

Implementation Time

Justin Massa

GenAI for SMBs

Remix Partners

Connect ↓

The Challenge

A 70-year-old California custom manufacturer with 40,000 SKUs had a painfully manual quoting process. Custom specs flowed into a legacy software system, were manually re-entered into a second system, which then advanced the bill of materials and generated an RFQ response. The team consistently missed their 48-hour turnaround target and spent significant time on back-and-forth with customers to collect missing information.

What They Built

The client had already used Gemini to build internal tools but hit the ceiling without software engineering expertise — Remix Partners came in to do what the client couldn't do alone. They built an AI workbench inside Claude Code over 3.5 weeks, starting with a foundational unlock: converting the legacy software output into JSON. That single transformation made proprietary data machine-readable and opened a cascade of downstream automation. The workbench now receives an RFQ, compares it against the full 40,000-item catalog, generates a bill of materials, notifies the right people, converts it to customer-ready pricing, and produces a first-pass manufacturing drawing — all before a human touches it. The engineers were skeptical until they saw the prototype built from their own data. After that, they became the project's loudest advocates.

Remix Partners identified that the client's core obstacle wasn't ambition — they had already built Gemini-based internal tools — it was data access. The legacy software produced proprietary output formats that no downstream system could read. The first and most critical step was converting that output to JSON, which made 40,000 SKUs and decades of manufacturing data machine-readable for the first time. That single transformation unlocked a cascade of downstream automation. Remix Partners then built the AI workbench inside Claude Code over 3.5 weeks. The workbench receives an RFQ, compares it against the full catalog, generates a bill of materials, notifies the right internal stakeholders, converts the BOM to customer-ready pricing, and produces a first-pass manufacturing drawing — all before a human reviews it. The engineers who had been skeptical about AI's applicability to their specific process became the project's loudest advocates once they saw the prototype operating on their own data.

AI Role

Claude Code serves as the AI workbench that orchestrates the entire quoting workflow. It receives an RFQ, compares it against the full 40,000-item catalog, generates a draft bill of materials, converts it to customer-ready pricing, produces a first-pass manufacturing drawing, and flags specification conflicts — all automatically before any human engineer reviews the output.

AI Model

ChatGPT

Infrastructure

Claude Code (AI workbench environment) • Legacy manufacturing software (output converted to JSON) • Gemini (prior internal tool foundation) • Custom catalog and BOM processing logic

Integration Points

Legacy software output converted to JSON via custom parsing layer • RFQ input connected to 40,000-SKU catalog comparison engine • BOM output linked to stakeholder notification and pricing conversion • Pricing output triggering first-pass manufacturing drawing generation

Impact

3.5 weeks

Complete build time for a custom AI workbench that replaced a multi-system manual process a 70-year-old company had run for decades

48-hr turnaround

RFQ turnaround time cut nearly in half from a baseline the team had routinely missed with their manual process

40,000 SKUs

AI workbench navigates the full parts catalog to match, price, and draft manufacturing drawings for every custom order

Technology Utilized

Implementation Complexity

Time Savings

Cost Reduction

The solution required a non-trivial foundational engineering step — converting proprietary legacy software output into JSON — before any automation could be built. The Claude Code workbench then integrates catalog comparison across 40,000 SKUs, BOM generation, pricing logic, drawing generation, and conflict detection, all tailored to a specific manufacturer's proprietary processes and data structures.

Best Fit For

Manufacturers running complex custom catalogs who are consistently missing quote deadlines — and have already tried the easy AI tools without fixing the underlying problem.

Justin Massa

GenAI for SMBs

Remix Partners

Former IDEO partner and founder of Food Genius (acquired by USFoods). Now co-founder of Remix Partners, helping 32+ companies operationalize GenAI across industries.

Connect with the Expert

Industry:

Manufacturing & Industrial

Business Function:

Operations

Sales & Revenue

Company Size:

251-1,000

Project Cost:

Cost not disclosed

Ownership:

Founder-Owned

Organization Type:

Private Company

AI Pattern:

Document Processing & Extraction

Generative Design & Content

Process Automation (RPA + AI)

Value Type:

Time Savings

Cost Reduction

AI Model:

Frequently Asked Questions

How did a mid-sized manufacturer halve RFQ turnaround with document-processing AI?

The experts found the real blocker was data access: the legacy software produced proprietary output no downstream system could read. Converting that output to JSON made 40,000 SKUs and decades of data machine-readable for the first time, unlocking the rest. They then built an AI workbench that receives an RFQ, matches it against the full catalog, generates a bill of materials, prices it, and drafts a first-pass manufacturing drawing, cutting RFQ turnaround nearly in half.

What AI tools and models were used at the manufacturer?

The workbench was built inside Claude Code, with the client's prior Gemini-based internal tools as the starting point, and the foundational unlock was converting the legacy software output into JSON. The approach combined document processing, generative content, and process automation.

What results did the manufacturer achieve?

RFQ turnaround was cut nearly in half to a 48-hour turnaround from a deadline the team had routinely missed, the workbench navigates the full 40,000-SKU catalog to match, price, and draft drawings for every custom order, and the complete build took 3.5 weeks.

How long did the build take?

The AI workbench was built in 3.5 weeks, inside a sub-four-week window.

Who is this document-processing AI approach best for?

Manufacturers running complex custom catalogs who are consistently missing quote deadlines and have already tried the easy AI tools without fixing the underlying data problem.