SketchMetrics

Project: SketchMetrics

Self-reported basis: The description is entirely from the author’s own submission to a hackathon, unverified and without third-party corroboration.

What it appears to be: A desktop application that analyzes hand-drawn floor plans using AI and image processing tools, aimed at architecture students and professionals for educational purposes. It focuses on identifying errors and explaining design principles rather than automating design.

What changed: The project was submitted as part of a hackathon; no evidence of prior development or commercial activity is provided.

Most important open question: Is there any evidence of user adoption, revenue, or traction beyond the author's own account?

The description states that SketchMetrics is an AI tool for architects and architecture students that analyzes hand-drawn floor plans. It builds a structured building model from imported images, allows users to assign floors, straighten drawings, set scale by selecting a known edge, review rooms and openings, and explore insights such as circulation, visibility, and sun exposure.

• Functionality: Converts floor-plan images into structured models.
• User workflow: Import plans, adjust scale, review elements, explore insights.
• Storage: Projects are saved locally.
• Technology stack: Built with Kivy (UI), FastAPI (backend service), OpenCV (image processing), TopologicPy (geometry/space analysis).
• AI role: Used for guiding implementation steps and modular development; not described as core AI functionality in the product itself.

Note: The author states that the tool is built using open-source technologies, but no evidence of commercial use or integration with existing platforms is provided.

The description claims that SketchMetrics is designed for education over automation. It aims to build critical thinking by flagging mistakes and explaining design principles, rather than simply generating outputs.

• Positioning: Educational tool focused on learning design principles.
• Core claim: Builds critical thinking instead of automating tasks.
• Evolution: The project evolved from a hackathon submission into a desktop application with a guided workflow.
• AI use: AI is used in development, not necessarily in the end-user experience.

Inference: The product may be positioned as an educational aid for architecture students or early-career architects. However, this is based on self-reporting and lacks evidence of actual user feedback or market traction.

The description identifies two main target groups:

• Architecture students
• Architects (and others who want to design buildings)

It also notes that the tool is intended for anyone interested in building design.

• Primary users: Architecture students and professionals.
• Secondary users: Anyone involved in architectural design or education.
• ICP: Not clearly defined beyond broad categories; no segmentation or persona details provided.

Not evidenced: No evidence of specific customer segments, usage patterns, or feedback from target users.

There is no mention of pricing, monetization strategy, or business model in the description.

• Pricing: Not stated.
• Monetization: Not described.
• Business model: Not evident.

Inference: If this is a desktop tool, it might be sold as a one-time purchase or subscription. However, no evidence supports any such model.

The project was built using:

• Kivy (for UI)
• FastAPI (backend service)
• OpenCV (image processing)
• TopologicPy (geometry and spatial analysis)

It also mentions use of AI for development planning via Codex with GPT-5.6 Terra.

• Tech stack: Desktop application, open-source tools.
• Development approach: Modular implementation using AI-assisted coding.
• AI in development: Used to trace changes across interface, backend, tests, and documentation.
• Image processing: Focus on vectorizing skewed or low-quality photos.

Not evidenced: No evidence of scalability, cloud integration, API access, or deployment infrastructure beyond local desktop use.

The project was submitted to a hackathon (OpenAI 2026), and there is no indication of prior traction, revenue, or user adoption.

• Traction: None reported.
• Maturity: Early-stage prototype; built in a short timeframe.
• User feedback: Not provided.
• Market validation: Not evident.

Inference: The tool appears to be a proof-of-concept or early prototype with no known users or commercial activity.

No mention of competitors is made in the description. The author does not reference similar tools or platforms in the architecture or design space.

• Competitors: Not identified.
• Market context: Not described.
• Differentiation: Based on educational focus and critical thinking over automation.

Not evidenced: No competitive landscape, pricing comparisons, or market positioning relative to existing tools.

Several risks and red flags emerge from the lack of evidence:

• The project is self-reported and unverified.
• No revenue, customers, or traction data are provided.
• The tool appears to be a hackathon prototype with no commercial history.
• AI is used in development but not in core product functionality.
• Lack of clarity on how the tool would scale beyond a single developer.

Inference: Without evidence of adoption or monetization, the project may not have reached a viable market stage.

1. What is the current user base or feedback from architecture students or professionals?
2. How does the tool handle real-world complexity in floor plan images (e.g., poor lighting, distortion)?
3. Are there any plans to monetize the product or integrate with existing design platforms?
4. Has the tool been tested by actual architects or educators in a classroom setting?
5. What are the technical limitations of the current vectorization process?
6. How does the AI-assisted development approach scale beyond one developer?