Inada Manufacturing produces precision massage chairs for global markets. Each custom configuration quote required a six-hour manual process. We built QuoteForge — an AI pipeline that returns a complete quote in 48 seconds.
Inada Manufacturing produces high-precision massage chairs sold into hotel, medical, and retail markets globally. Each product line supports hundreds of configuration variables — motor specifications, upholstery options, localization requirements, logistics zones, and custom branding.
Quoting a custom configuration meant a sales engineer manually cross-referencing five separate sources of truth:
The process took six hours per inquiry. At peak inquiry volume, that created a three-to-five day backlog.
Inada needed a system that could ingest incoming specification documents — often PDFs or structured emails from distributors — and return a complete, accurate quote without human intervention.
The pipeline uses Gemini 2.5 Flash for document understanding — its vision capability handles non-standard PDF layouts, hand-annotated spec sheets, and mixed-language inputs. Claude 3.5 Sonnet handles the reasoning layer: applying Inada's pricing rules, resolving ambiguous option combinations, and flagging edge cases for human review rather than guessing.
Every decision in the pipeline is logged to MongoDB with the model's confidence scores and the input state — giving Inada a complete audit trail for every quote, whether or not a human reviewed it.
QuoteForge went live in Q3 2024. Quote turnaround dropped from an average of six hours to 48 seconds. The backlog cleared within two weeks of deployment. The sales team reports handling three times the inquiry volume with the same headcount.
Edge cases — configurations the model flags with low confidence — are routed to a human review queue. This accounts for roughly 4% of inquiries and takes 20 to 30 minutes rather than six hours, because the model pre-fills everything it can.
The initial version used a single model for both extraction and reasoning. Splitting these into two discrete model calls — one fast and cheap for extraction, one capable for reasoning — reduced latency by 30% and cost per quote by 45%.
We would also build the human review queue before the first deployment rather than retrofitting it. The initial assumption was that confidence scores alone would be sufficient signal. They are not. A structured review interface should be part of v1.
If your team runs a manual workflow more than 50 times a month, and the inputs arrive as documents rather than clean data, there is a good chance the bulk of it can be automated with the same extract-then-reason split used here.
Tell us about the workflow. We will tell you honestly whether AI is the right tool for it, and what it would take to build.