Published

How a Custom Manufacturer Cut Engineering Time 60%

A custom manufacturer's engineers handed RFQs to an AI workbench that drafts BOMs, quotes, and production drawings — targeting a 60-70% cut in engineering time per order.

60–70%

Reduced engineering time per order

6–12 months

Implementation Time

Not disclosed

Project Cost

the challenge

A California-based custom manufacturer with 40,000 SKUs and a 70-year operating history came to Remix Partners after hitting the ceiling of what their internal team could build. Their RFQ process was deeply manual — engineers printed specs from legacy software, manually re-entered data into a second system, advanced a bill of materials by hand, and generated quotes through constant back-and-forth with customers. Their target of 48-hour RFQ turnarounds was almost never achieved.

what they built

Remix Partners ran their GenAI Kickstart process — interviews with engineers, operations leads, and the executive team to map workflows and identify the highest-leverage friction points. Their first move was converting the output of a legacy software system into JSON, which unlocked downstream automation. Over 3.5 weeks they built a Claude Code-based workbench that: ingests an RFQ, compares it against all prior parts the company has made, generates a draft bill of materials, notifies team members, converts the draft BOM into a price quote, and takes a first pass at production drawings. Custom AI validation flags specification conflicts before they reach the floor. Engineers review and refine a 90% complete draft rather than starting from scratch.

Remix Partners started with their GenAI Kickstart process — structured discovery interviews with engineers, operations leads, and the executive team to map the quoting workflow and identify the highest-leverage friction points. One finding stood out: the legacy software system produced proprietary output that was unreadable by other systems, making automation impossible until that was solved. Their first move was converting the legacy system's output into JSON — a foundational unlock that made every downstream automation step possible. From there, over 3.5 weeks, they built a Claude Code workbench covering the entire RFQ-to-production workflow: the system ingests an incoming RFQ, compares it against all 40,000 prior parts the company has manufactured, generates a draft bill of materials, notifies team members, converts the draft BOM into a price quote, and takes a first pass at production drawings. Custom AI validation flags specification conflicts before they reach the manufacturing floor. Engineers no longer start from scratch — they review and refine a 90% complete draft, freeing experienced staff from routine documentation for the complex, high-value designs where real competitive differentiation lives. Projected outcome: 60–70% reduction in engineering time per customer order.

best fit for

CEOs, COOs, and CFOs at companies up to 500 employees (with expansion into mid-market and Fortune 500) across professional services, manufacturing, life sciences, healthcare, VC/PE, and nonprofits — specifically leaders who know AI matters but are overwhelmed by the noise and need a trusted partner to cut through it and deliver real results, not demos.

Ai ROLE

Claude Code powers the AI workbench that processes inbound RFQs end-to-end. It ingests a request, compares it against the full 40,000-item catalog of prior parts, generates a draft bill of materials, converts it to a customer-ready price quote, takes a first pass at production drawings, and flags specification conflicts — all before a human engineer reviews the output.

impact

60–70% Reduction in Engineering Time Per Order (Projected)

Design print automation is projected to reduce the engineering time required per customer order by 60–70%. The engagement was still in early phases at time of interview — this is a projected, not yet realized, outcome.

Senior Engineers Freed for Complex, High-Value Work

Rather than spending time on routine documentation for every order, experienced engineers can now focus on complex and novel designs — where real competitive differentiation lives. The CFO described the shift from documentation to creative problem-solving as "transformative."

Quote-to-Production Workbench Built in 3.5 Weeks

In three and a half weeks, Remix Partners built a working workbench covering every stage from customer RFQ to production-ready drawings — a foundation that previously had no automation at any stage.

implementation complexity

The solution required converting a legacy software system's proprietary output format into JSON — a non-trivial foundational unlock — followed by building a multi-step Claude Code workbench integrating catalog comparison, BOM generation, pricing logic, drawing generation, and conflict validation. This level of custom development and legacy system integration is well beyond off-the-shelf tooling.

Jason Rubinstein

Partner & Co-Founder @ Remix Partners

Remix Partners

30+ years leading product and AI initiatives at Cisco, EmployBridge, and Uptake. Co-founder of Remix Partners, helping businesses turn GenAI experiments into growth engines. Holds 13 U.S. patents.

Get an intro

Talk to this team

industry

Manufacturing & Industrial

business organization

Operations

Sales & Revenue

AI TYpe

Document Processing & Extraction

Generative Design & Content

Process Automation (RPA + AI)

value type

Time Savings

Cost Reduction

other(firm) Case studies

frequently asked questions

How did a mid-sized manufacturer aim to cut engineering time per order 60–70% with AI process automation?

The experts ran structured discovery to map the RFQ-to-production workflow, then made a foundational unlock by converting the legacy system's proprietary output into JSON. Over 3.5 weeks they built an AI workbench that ingests an RFQ, compares it against all 40,000 prior parts, drafts a bill of materials, generates a quote, and takes a first pass at production drawings, so engineers refine a 90%-complete draft. The 60–70% reduction in engineering time per order is a projected outcome, as the engagement was early-stage at interview.

What AI tools and models were used at the manufacturer?

The workbench was built with Claude Code, with Gemini also used, plus custom AI validation that flags specification conflicts before they reach the floor. A key unlock was converting the legacy system's proprietary output into JSON. The approach combined document processing, generative content, and process automation.

What results did the manufacturer achieve?

A quote-to-production workbench covering every stage from RFQ to production-ready drawings was built in 3.5 weeks, where no stage had any automation before, and senior engineers were freed from routine documentation for complex, high-value design work. The headline 60–70% reduction in engineering time per order is projected, not yet realized.

How long did the engagement take?

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

Who is this AI engineering-automation approach best for?

CEOs, COOs, and CFOs at companies up to roughly 500 employees, expanding into mid-market and larger firms, across professional services, manufacturing, life sciences, healthcare, and VC/PE, who know AI matters but need a trusted partner to deliver real results rather than demos.

Have a similar challenge?

Ask whether this would work for you, or describe what you're trying to solve.

TELL US WHAT YOU'RE EXPLORING