LuxePlatforms
Rather just talk?(816) 477-6802hello@luxeplatforms.comKansas City · Building nationwide
AI Tooling · Construction08 / 16

A vision server that lets an AI read construction linework straight off PDF drawing sheets

Lets an AI actually see construction drawings, not just read their text.

The visual half of an automated millwork takeoff: it renders any drawing sheet or sub-region to a crisp image and returns it as model-readable content, so a vision model can count doors, drawers, shelves, and finished ends that are drawn, not labeled.

In production

A look at the interface.

Representative UI — abstracted, never a client's real data.
🔒app.workspace.dev/overview
Studio
Overview
Analytics
Projects
Inbox3
Reports
Team
Settings
Storage68%
Workspace/Overview
Search…
Overview
Last 30 days · updated 2m ago
Last 30 daysNew report
Revenue
$128.4k
12.5%
Active users
8,642
4.1%
Conversion
3.84%
0.6%
Avg. session
4m 12s
8.2%
Performance
RevenueTarget
JanFebMarAprMayJun
Recent activity
Atlas migration
$24,800
Active
Onboarding flow
$11,250
Review
Billing revamp
$38,400
Active
Mobile parity
$9,600
Done
Dashboard / ops console · representative UI
AI
Reads plans like an estimator
Any
Works on any PDF plan set
Auto
Counts doors, drawers & finishes
Role
Solo, backend + AI
Year
2026
Status
In production
Category
AI Tooling · Construction
Built with
  • Python
  • MCP
  • PyMuPDF
  • Pillow
(01) The Challenge

The industry's measurement tool returns text only, dimensions and callouts, and can't see drawn detail like a door-vs-drawer split or a finished end. Those distinctions are drawn, not written, so a separate server was needed to expose the visual half of a takeoff.

(02) The Approach

How it
works

The industry's measurement tool returns text only and can't see drawn detail like a door-vs-drawer split. This server renders any sheet or normalized sub-region to a crisp image and returns it as model-readable content. Find a sheet by full-text search, render it with a coordinate grid, then zoom a region at higher resolution to count detail. Every render is capped to a configurable pixel budget.

What I built

(03) Inside the build
01

Navigate-then-zoom workflow

Find a sheet by full-text search, render it with a coordinate grid for an overview, then zoom a normalized sub-region at higher resolution to count detail.

02

Exhaustive tile sweeps

Slice a sheet into high-resolution tiles for complete coverage when a single render would miss fine linework.

03

Megapixel budgeting

Every render is capped to a configurable pixel budget, auto-reducing resolution and reporting it instead of emitting a giant payload.

(04) Highlights

The
receipts

  • Returns native image content so a vision model reads drawings directly
  • Sheet addressing by page, sheet code, or text search
  • Works on any PDF drawing set, with no proprietary software running
  • Automatic resolution governance keeps payloads sane
← Previous
Run a Millwork Shop in Plain English
Next →
Pre-Bid Construction Estimating Engine