Manufacturing · Building materials
Panel specs from CAD drawings in seconds, not hours
Reads DWG/DXF layouts and builds the Excel spec: 10–30 seconds instead of 2–15 hours by hand. All 784 panels of one real project matched the manual spec line by line.
- Status
- MVP in operation
- Timeline
- 6 weeks
- Stack
- Python
- ezdxf
- ODA File Converter
- openpyxl
- customtkinter
- PyInstaller
The task
A sandwich panel manufacturer lays out each project in CAD, then counts hundreds of panels by hand and types the spec into Excel. On real projects this took 2–15 hours, and 1 to 15 days passed between a finished drawing and a spec sent to the customer. Drawings were marked up inconsistently, with text tags on some and dimensions only on others, so a simple parser would not do.
What we built
- We built a drawing-to-spec pipeline: the app reads DWG/DXF, finds the panels, groups them and writes an Excel file in the client’s own template.
- Three recognition strategies cover the different markup styles: text tags, dimension chains and block attributes. The app suggests a mode, and a new project needs a config change rather than code.
- Engineers kept their usual CAD workflow: the app works with the existing drawing markup, and the designer confirms detected panels in a table before export.
- Shipped to workstations as a standalone Windows app with one-click install and on-demand updates. Output was verified against hand-made specs line by line and by totals.
- The next stage, from spec to quotes, orders, production and inventory, is designed and written up as a development plan. It was outside this scope and is not built.
Outcome
- 784/784 and 189/189
- panels on one project and wall panels on another matched the manual specs line by line, size groups included; area within 0.001 m²
- 2–15 h → 10–30 s
- to produce a project spec: manual work vs app processing, measured on real projects
- 40–200 h/month
- potential engineering time saved at 20–30 projects a month, per the project’s economics model
- 1–3 months
- estimated payback, per the project’s economics model
Services
More cases
Real estate · PropTech marketplace
MVP in operationLand-plot marketplace with a next-step plan: MVP in 2 months
From a mock-up to a working platform: plot → works → contractor → request. Rule-based next-step engine, three dashboards, personal-data compliance. MVP in 2 months.
- 2 months
- from approved spec to a pre-release MVP on an HTTPS stand: week 9 against the plan’s own 10–13 week estimate
- 7 days
- from spec to the first full-implementation commit: 168 files, 21.5k lines, then two months of hardening to pre-release
EdTech · HR-tech
MVP in operation (demo stand)From business canvas to a student-work marketplace demo in about six weeks
The client had a business model and no product. We built a student-task marketplace MVP where the server enforces legal and platform rules, and put a demo stand live.
- ~6 weeks
- from first commit to a deployed demo with all workspaces; 7 working days in commit history
- 3 checks
- run by the server before a contractor is assigned: data consent, self-employed status, mentor; each with a plain refusal
Marketplace e-commerce · Pricing
PilotRule-based repricing: a pilot whose contract terms are enforced in code
Competitor prices tracked per SKU, a price computed by rules inside an agreed corridor and applied only after confirmation. Pilot: 10 SKUs, setup within 14 days.
- 10 SKUs · 2 scenarios
- pilot scope; the SKU cap and both scenarios are enforced in code and verified by contract tests, so the cap cannot be exceeded
- up to 14 days
- contractual setup window from client inputs to launch, then a 1-month pilot; the service tracks the dates and closes access when the period ends
Estimate the payback of a similar process
AVA lets you work out the economics of your process on your own figures, with no form and no price from us. It shows what the manual work costs, what cash effect automation would give and what budget would pay back. If the effect does not even cover running costs, it says so.
Estimate the paybackDiscuss a similar problem
Describe the process and the data you have. Before any work starts we will tell you what can be measured in money, what cannot, and whether it is worth doing.