ShadeWise

ShadeWise is a self-reported OMR (Optical Mark Recognition) solution for secondary schools that uses photographed answer sheets rather than dedicated scanning hardware. The project was built during the OpenAI 2026 hackathon using Codex, GPT-5.6, Django, OpenCV, and Python. It claims to enable teachers to automate marking while retaining human review for confidence-based decisions.

The author states that ShadeWise is an extension to an existing school portal, built with AI assistance, and designed to reduce the time and stress of marking while maintaining accuracy through AI and human oversight. The system is described as being tuned for a fixed bracket-box answer-sheet template, with future enhancements planned for additional templates, bulk uploads, QR identification, annotations, and theory marking.

Key commercial due-diligence questions remain open: whether the solution has been adopted by any schools or teachers; if there are any revenue streams or business model elements beyond the author's own use case; what the actual accuracy of the AI is in real-world conditions; how it compares to existing OMR tools or manual marking; and whether the author intends to commercialize or scale the product.

The description states that ShadeWise is a teacher-centred OMR workflow for schools using photographed answer sheets. It uses AI (specifically GPT-5.6) to process these sheets without requiring dedicated scanning hardware.

It includes:

• A Django-based assessment workflow
• An OpenCV calibration and extraction pipeline
• Handling of photographed-sheet frame/serial-row data
• Confidence-based human review functionality
• Raw-score analysis and exports
• Automated tests

The system is described as being tuned for a fixed bracket-box answer-sheet template, with future features planned such as support for additional templates, bulk uploads, QR/student identification, annotations, and theory marking.

Inference The product appears to be a proof-of-concept or prototype built during a hackathon, not yet a commercial-grade solution. It is not evidenced to have been deployed in production environments beyond the author’s own classroom.

The description states that ShadeWise was developed by a teacher who wanted to reduce the stress and time involved in marking answer sheets using AI, while still allowing for human review when confidence is low. The author notes that the solution was built with ChatGPT and GPT-5.6, and that it integrates into an existing school portal.

The positioning is:

• Teacher-focused
• AI-assisted OMR
• Designed for schools without scanning hardware
• Emphasizes accuracy and human review

Inference The product's positioning appears to be a niche solution for educators seeking automation in marking, but there is no evidence of market validation or broader adoption.

The description states that ShadeWise is intended for secondary schools using photographed answer sheets. It is built for teachers who want to automate marking while retaining human review for confidence-based decisions.

Inference The target customer is a single teacher or small group of teachers within a school, not a broader market segment. There is no evidence of a defined ICP beyond the author’s own use case.

The description does not provide any information on pricing, monetization, or business model elements. It states that the solution was built for personal use and to help colleagues benefit from it at little to no cost.

Inference No commercial business model is evidenced. The author’s intent appears to be personal or collaborative use rather than a scalable product with revenue streams.

The project was built using:

• Codex
• GPT-5.6
• Django
• OpenCV
• Python

It includes:

• A Django-based workflow
• OpenCV calibration and extraction pipeline
• Handling of photographed-sheet frame/serial-row data
• Confidence-based human review
• Raw-score analysis and exports
• Automated tests

The current version is tuned for a fixed bracket-box template, with future enhancements planned.

Inference The technical stack suggests a prototype or hackathon-level solution. There is no evidence of scalability, robustness, or production-grade delivery beyond the author’s own use case.

The description states that the project was built during a hackathon and is an extension to an existing school portal. It is not evidenced to have been adopted by other schools or teachers beyond the author's personal experience.

There is no evidence of:

• Customer adoption
• Revenue
• User feedback
• Product maturity or iteration history

Inference The product has no demonstrated traction or market validation. It remains a self-reported prototype with no external use or testing.

The description does not provide any information on competitors or the broader OMR market. It is unclear whether there are existing tools for OMR in educational settings, or how ShadeWise compares to them.

Inference No competitive context is evidenced. The project appears to be a standalone solution with no known market positioning or comparison to other tools.

• No commercial traction or adoption: The product has not been used beyond the author’s own classroom.
• Unproven accuracy: While the author claims AI results were “amazing,” there is no data on actual performance.
• Limited scope: The system is tuned for a fixed template and lacks features like bulk uploads, QR identification, or theory marking.
• No business model: No evidence of monetization or scalability beyond personal use.
• Self-reported only: All claims are unverified and based solely on the author’s account.

1. Has ShadeWise been tested with other teachers or schools, and what feedback have you received?
2. What is the accuracy rate of the AI in real-world conditions, and how does it compare to manual marking?
3. Are there any plans to monetize or scale this product beyond personal use?
4. How does the system handle variations in answer sheet formats or poor image quality?
5. What are the technical limitations of the current version, and what features are planned for future releases?