A 70-Year-Old Manufacturer Cut RFQ Turnaround Nearly in Half With Claude Code
A Claude Code workbench built in 3.5 weeks matches each RFQ against a 40,000-SKU catalog and drafts the bill of materials, pricing and a first-pass drawing, cutting quote turnaround nearly in half for a team that used to miss its 48-hour target.
Who this is about: Custom manufacturer (70 years old, California, 40,000 SKUs)
What it takes
- Cost
- Free planClaude: Free plan. Pro is $20 a month billed monthly ($17 a month billed yearly), and Max starts at $100 a month. Team seats are $25 a month billed monthly.Price checked Oct 24, 2026 on claude.com. Prices change; check before you buy.
- Setup time
- A few weeksOur estimate from the source, for one business.
- Skill needed
- Developer skillsYou build or run your own code, even if AI writes it.
Explain it simply
When a customer asks for a price, the company used to retype the request into old software by hand. Consultants taught Claude Code, an AI coding helper, to read those requests, match them to the product catalog, and draft a parts list, price, and first drawing for an engineer to check. That cuts the waiting time before a quote goes out.
What was done
Custom specs used to go into a legacy system, get re-keyed by hand into a second system, and then become a BOM and RFQ response. The consultants first converted the legacy software's proprietary output into JSON so the data was machine-readable.
They then built a workbench in Claude Code that receives an RFQ, compares it with the full catalog, drafts the BOM, notifies the right people, converts it to customer pricing, flags spec conflicts and produces a first-pass drawing before an engineer reviews it.
How it went
RFQ turnaround was cut nearly in half; the team had routinely missed its 48-hour target before. The case study gives no before-and-after times, and only its FAQ says it now meets 48 hours. The build took 3.5 weeks. Engineers who were skeptical became supporters once they saw a prototype running on their own data.
- Limits: this is a case study of the consultancy's own project, published on Pluris, and the project cost isn't disclosed. The same page also lists "6–12 months" as implementation time, which doesn't match the 3.5-week build and isn't explained. The JSON conversion was a real engineering step, not a quick prompt.
- Engineers still review every output.
Prompt
Step 0: Export legacy system output and convert it to JSON (catalog, past BOMs, pricing).
Workbench steps for each RFQ:
1. Read the RFQ and compare it against the full catalog.
2. Draft a bill of materials.
3. Flag specification conflicts or missing information.
4. Convert the BOM to customer-ready pricing.
5. Produce a first-pass manufacturing drawing.
6. Notify the right internal people for human review.The workflow the case study describes; no prompts were published.
Business fit
Who this helps, and how:
Mechanics and tradespeople: match a new job request against your past jobs and parts list to draft a quote for review.
Local & serviceStartup founders and e-commerce sellers: for custom or made-to-order products, draft a parts list and price from the order form automatically.
Shopify & ecommerceRetail store owners: for special orders, check requests against your catalog and flag missing details before replying.
Local & serviceAgencies and freelancers: start any automation project by getting the client's old system exports into a clean, readable format.
Agencies
Related
- Evidence grade CA Revenue Team That Had Never Shipped Code Built Its Own Call Review Tools in Claude CodeVendor or secondhand, using Claude Code, n8n and Clay
- Evidence grade BA Salon Owner Built Booking-Abandonment Recovery With Claude; 17.3% of Lost Bookings Came BackStrong evidence, using Claude Code, Supabase and Vercel
- Evidence grade BAn Austin Realtor Kept 6 of 28 Claude Workflows, Including a CRM Sweep That Turned Up a DealStrong evidence, using Claude, Claude Code and Follow Up Boss
- AI for sales prospecting examplesDepartment hub: AI for sales, 34 examples
Similar tools
Other tools for this job, and how they differ. Chosen by our editors, never paid for.
- Cursor
Another AI coding environment for building an internal quoting workbench against your own catalog data.
- GitHub Copilot
Assists inside an IDE when engineers are writing the quoting logic themselves rather than generating a full app from chat.
- ChatGPT
Useful for drafting BOM and pricing logic in plain language before a developer wires it to legacy systems.
“Vendor or secondhand” (grade C) means: A tool maker's case study, a promotional demo, or someone else's write-up. How we grade. Spotted a mistake? Suggest a correction.