All Work
KPS Mart - Cutting Time-to-Proposal Without Adding Headcount hero image
Enterprise SoftwareOverview

KPS Mart

Cutting Time-to-Proposal Without Adding Headcount

TL;DR

01

Built a computer vision and LLM pipeline that converts CAD and PDF floor plans into draft furniture proposals with good/better/best budget tiers, reducing time-to-quote from weeks to 22 minutes.

02

Automated the first 80% of the proposal process so KPS designers focus only on review and refinement, dramatically increasing proposal capacity without adding headcount.

03

Developed a product catalogue digitization system using computer vision to extract furniture dimensions and specs from manufacturer images and data sheets into structured JSON for use in the recommendation engine.

The Challenge

KPS Mart has been designing interior spaces and selecting furniture for clients for over 30 years, primarily for offices and gyms. Their core deliverable is a general arrangement: a detailed design proposal showing furniture placement, product selections, and cost estimates tailored to the client's space and budget.

The problem was time. Creating a single proposal required designers to manually interpret CAD floor plans, identify room types and zones, cross-reference a product library of over 10,000 items across multiple manufacturers, and compile SKU-level selections with budget options. A project could take a team weeks from first floor plan to finished proposal.

This bottleneck capped how many concepts KPS could present to clients and how quickly they could iterate when clients asked for changes. The business wanted to increase the number of proposals generated, reduce the cost of creating each one, and give clients more options faster. But hiring more designers was not a scalable answer. KPS needed a way to automate the heavy lifting of proposal generation while keeping their designers in control of the final output.

Client Testimonial

"It took me 22 minutes from when I started until it was done, and it used to take that project team a couple of weeks."

Viktor, Senior Director at KPS

Key Results

01

Time-to-proposal reduced from weeks to 22 minutes

02

Designers now handle only the final 20% of the proposal process

03

10,000+ product catalogue digitized and made machine-queryable

04

Good/better/best budget tiering generated automatically per proposal

05

Increased proposal capacity without adding headcount

The Solution

01

Computer Vision for Floor Plan Interpretation

The first step in any KPS proposal is understanding the space. Designers work from CAD files exported as PDFs, which contain floor plan layouts, architectural symbols, room labels, dimensions, and zone annotations.

AE built a computer vision pipeline that ingests these CAD and PDF floor plans and automatically identifies furniture placement areas, architectural symbols, room types, zone boundaries, and spatial dimensions. What previously required a designer to manually interpret is now extracted programmatically, creating a structured representation of the space that feeds directly into the recommendation engine.

02

Object Classification and Furniture Identification

Beyond reading the floor plan layout, the system classifies each furniture element in the plan, identifying item types and assigning accurate counts per zone. This object classification step ensures the recommendation engine knows exactly what categories of furniture are needed in each area of the space before making any product selections.

This is a critical accuracy gate. Misclassifying a lounge chair as a desk chair, or undercounting workstations in an open plan area, would cascade into incorrect proposals. The classification layer was built to handle the variability in how different architects and designers represent furniture in CAD exports.

03

SKU Recommendation with Budget Tiering

With the space understood and furniture needs classified, the system matches requirements against KPS's product library to generate selections. KPS manages over 10,000 products across multiple manufacturers, each with its own dimensions, finishes, and price points.

The recommendation engine accounts for spatial constraints, client requirements, and budget to produce three tiers of options for each proposal: good, better, and best. This gives clients real choices and gives KPS designers a structured starting point rather than a blank page. Previously, generating these tiered options manually was one of the most time-consuming parts of the process.

04

Product Catalogue Digitization

Before the recommendation engine could work effectively, KPS needed their product library in a structured, machine-readable format. Manufacturer data arrives in inconsistent formats: PDF data sheets, product images with embedded dimension callouts, and multi-language specification tables.

AE built a computer vision pipeline to extract furniture dimensions, finishes, SKU codes, and pricing from manufacturer images and data sheets into structured JSON. This digitization work transformed KPS's 10,000-product catalogue into a format the recommendation engine could query reliably, and established a repeatable process for ingesting new products as the catalogue grows.

05

Human-in-the-Loop Designer Dashboard

Automation handles the first 80% of the proposal. The final 20% stays with KPS designers. AE built a review dashboard where designers can inspect the AI-generated proposal, flag any misclassified furniture items, swap product selections, and approve the final picks before they flow into the quoting system.

Critically, designer adjustments in the dashboard do not alter client-facing deliverables directly. The workflow keeps the AI output and the final proposal cleanly separated, ensuring designers remain in control of what goes to clients while still benefiting from the speed of automated generation.

Results

Key Metrics

Time-to-proposal reduced from weeks to 22 minutes

Designers now handle only the final 20% of the proposal process

10,000+ product catalogue digitized and made machine-queryable

Good/better/best budget tiering generated automatically per proposal

Increased proposal capacity without adding headcount

The Full Story

The system transformed KPS's proposal process from a weeks-long manual effort into a workflow that completes in minutes. Viktor, Senior Director at KPS, described the outcome directly: "It took me 22 minutes from when I started until it was done, and it used to take that project team a couple of weeks."

Designers now spend their time reviewing and refining AI-generated proposals rather than building them from scratch. The first 80% of the process is automated. The final 20% remains with the designer, preserving quality and client-specific judgment while eliminating the manual overhead that previously constrained how many proposals KPS could produce.

The result is a major increase in proposal capacity and speed without adding headcount. KPS can now present more concepts to clients, iterate faster on feedback, and deliver better-tiered options across budget ranges. Faster proposals with higher quality and more options translate directly to improved client satisfaction and sales efficiency.

Conclusion

KPS Mart's proposal process went from a weeks-long manual effort to a 22-minute automated workflow, without adding headcount or sacrificing design quality. By combining computer vision for floor plan interpretation, an LLM-powered recommendation engine, and a human-in-the-loop review dashboard, AE Studio gave KPS's designers a system that handles the heavy lifting and leaves them to focus on what matters most: delivering great spaces for their clients.

Key Insights

1

Computer vision unlocks structured data from unstructured design files. CAD exports and PDFs contain rich spatial information that, once extracted automatically, can drive downstream automation that was previously impossible at scale.

2

Automating the first 80% is more valuable than automating everything. Keeping designers in the loop for final review preserves quality and client trust while eliminating the manual work that actually constrained capacity.

3

Product catalogue quality is a prerequisite for recommendation accuracy. Digitizing 10,000 products into structured JSON before building the recommendation engine was unglamorous work but essential to the system performing reliably.

4

Budget tiering increases proposal value. Giving clients good/better/best options in every proposal creates more decision-making flexibility and positions KPS as a more thorough partner than competitors who deliver a single option.

5

Internal tools can outperform client-facing products in ROI. Starting with an internal designer tool rather than a customer self-service product allowed KPS to move faster, maintain quality control, and prove the concept before broader deployment.

Frequently Asked Questions

KPS Mart's designers were spending weeks manually interpreting CAD floor plans, cross-referencing a 10,000-product catalogue, and assembling furniture proposals for commercial interior projects. This bottleneck limited how many proposals they could produce and how quickly they could respond to client feedback. They needed a way to automate the most time-intensive parts of the process without removing designer judgment from the final output.
The system ingests CAD files exported as PDFs and uses computer vision to identify furniture placement areas, room types, zone boundaries, architectural symbols, and spatial dimensions. This produces a structured representation of the space that feeds directly into the furniture recommendation engine, replacing what was previously manual interpretation by a designer.
KPS manages over 10,000 products across multiple manufacturers. Before the recommendation engine could operate reliably, AE built a computer vision pipeline to extract furniture dimensions, finishes, SKU codes, and pricing from manufacturer images and data sheets into structured JSON. This catalogue digitization work was a prerequisite for accurate automated recommendations and established a repeatable process for adding new products over time.
For every proposal, the recommendation engine generates three tiers of product selections mapped to different budget levels. Clients can see options at each price point rather than receiving a single recommendation. This gives clients more flexibility in their decision-making and gives KPS designers a richer starting point for client conversations.
Designers review the AI-generated proposal through a human-in-the-loop dashboard. They can flag misclassified items, swap product selections, and approve final picks before they flow into the quoting system. The dashboard keeps designer adjustments separate from client-facing deliverables, ensuring quality control without requiring designers to rebuild the proposal from scratch.
Viktor, Senior Director at KPS, described the result firsthand: the process that used to take a project team a couple of weeks now takes 22 minutes. The system automates the first 80% of the proposal workflow, leaving designers to focus only on review and refinement.
OverviewEnterprise Softwareintermediate7 min readComputer VisionLLMProposal AutomationInterior DesignFurnitureHuman-in-the-LoopSKU RecommendationEnterprise SoftwareCAD ProcessingWorkflow Automation

Published: Jan 2025 ยท Last updated: Feb 2026

Ready to build something amazing?

Let's discuss how we can help transform your ideas into reality.

START A PROJECTVIEW MORE WORK