Math Dressing Studio

The description states that Math Dressing Studio is a composable and verifiable generator for leveled middle-school math problems, built as a one-page application using React, TypeScript, and Tailwind CSS. It uses a schema-driven approach to define:

• A Body containing the mathematical relationship, unknown, domain, answer, and target skill.
• A Layer that changes presentation or diagnostic support.

The system supports:

• Loading and verifying samples
• Removing or restoring Layers
• Exposing intentional Layer failures
• Applying bounded repairs
• Revalidating results

It is described as a curated demo, with no API requirement, and includes three original reviewed samples: geometry bar model, coordinate representation, and diagnostic-choice problem.

Inference The system is designed to ensure that changes in presentation do not silently alter the mathematical content being assessed — a claim of verifiability.

The author states that Math Dressing Studio began with the question: “Can we change how a math problem is presented without silently changing what it measures?”

It positions itself as:

• A tool for verifiable math problem generation.
• A system that separates creative presentation from mathematical integrity.
• A platform to expose diagnostic failures and repair them explicitly, rather than relying on aggregate scores.

The project is described as a Build Week MVP, suggesting it was not intended for production use but as a proof-of-concept or prototype.

Inference The positioning reflects a focus on educational integrity and transparency, but there is no evidence of market positioning or competitive differentiation beyond its self-described features.

The description states that the tool is designed for:

• Middle-school math educators
• Curriculum authors
• Educational content creators

It is described as targeting a "leveled middle-school math problem" context, with a focus on:

• Diagnostic support
• Representation variety (geometry, coordinate)
• Answer uniqueness and shortcut risk control

There is no mention of:

• Specific customer segments beyond educators
• End-users (students)
• Institutional adoption or licensing models

Inference The ICP appears to be educators and curriculum developers, but no evidence of specific customer personas, usage patterns, or feedback exists.

There is no evidence in the description of:

• Revenue streams
• Pricing models
• Monetization strategy
• Customer acquisition plans
• Subscription or licensing structures

The project is described as a Build Week MVP, with no indication of commercial intent or product-market fit.

Inference There is no evidence of a business model beyond the author’s own prototype work.

The project is built using:

• Next.js
• React
• TypeScript
• Tailwind CSS
• Zod for schema validation
• Vitest for testing
• OpenAI GPT-5.6 (server-side only, in optional repair route)
• Codex for development support

It includes:

• A Git history for inspectability
• Deterministic validation logic
• Strict schemas for all components
• Bounded repair mechanisms
• Failure inspection and revalidation

The system is described as:

• Stable in curated mode
• Not requiring an API for the demo
• Using a server-side route with strict schema validation before model use

Inference The technical stack suggests a lightweight, schema-driven prototype, not a full-scale SaaS product.

There is no evidence of:

• Revenue
• Customers or users
• Product-market fit
• Adoption metrics
• Growth data
• Live usage or production deployment beyond the demo

The project is described as:

• A Build Week MVP
• A curated demo with no student data
• Stable and independently testable
• Not yet live in a production environment

Inference The project is at a very early stage, with no evidence of traction or maturity beyond the author’s own work.

There is no evidence in the description of:

• Competitors
• Market positioning
• Product differentiation
• Existing tools in the math problem generation space

The tool is described as a self-contained prototype, not part of an existing marketplace or product ecosystem.

Inference There is no evidence of competitive context, market positioning, or differentiation from other tools.

Key risks and open questions include:

1. No commercial traction or adoption — the tool is a demo with no evidence of real-world use.
2. Limited scope — only three samples, one Body type, and one team member.
3. No API or live functionality — the system is not yet production-ready.
4. Unproven model integration — GPT-5.6 is used in an optional route but not proven to work in practice.
5. No pricing or monetization strategy — no indication of how it would be sold or funded.
6. Single founder — the team size is listed as one, which may limit scalability.

Inference The tool is in an early prototype phase, with no evidence of viability or commercial readiness.

1. What specific feedback have you received from educators or curriculum developers?
2. How do you plan to expand beyond the current three samples and one Body type?
3. Are there any plans for live API integration, or is it intended to remain a demo?
4. What are your long-term goals for monetization or product-market fit?
5. How do you intend to scale from a single developer to a production-ready system?
6. Have you tested the bounded repair functionality with real-world educators?