BodyMap

What the company appears to be: BodyMap is a computer-vision-based tool designed for movement instructors (e.g., pole dance, dance, weightlifting teachers) to provide visual coaching feedback by overlaying recommended body poses on student videos. The author describes it as an application that allows instructors to capture a moment from a student’s movement video, adjust a pose overlay to demonstrate the correct position, and share this as an animated review or downloadable video.

What changed: The project was built as part of a hackathon submission (OpenAI 2026) by one developer, Steven Chu. It represents a self-contained prototype with no evidence of prior traction, revenue, or customer adoption.

Single most important open question: Is there any evidence that movement instructors are interested in using this tool beyond the author’s personal experience as a pole dance instructor?

The description states that BodyMap is a React and TypeScript application built with Vite, using MediaPipe Pose Landmarker for body landmark detection. It allows instructors to:

• Upload a movement video
• Capture a key moment
• Confirm or adjust detected pose landmarks
• Create a recommended pose overlay
• Annotate changes with coaching notes
• Generate an animated review or downloadable MP4

The tool integrates Supabase for authentication, media storage, and project management, and uses a separate FFmpeg rendering service to produce shareable videos.

Inference: The system is a hybrid of computer vision (for pose detection), UI editing (for overlay adjustment), and video rendering (for output). It is not described as a SaaS platform or marketplace but rather a desktop/mobile tool for individual instructors.

The author claims that BodyMap helps movement teachers provide more effective coaching by turning verbal feedback into visual coaching artifacts. The core idea is to help students better understand corrections through animated transitions between original and recommended poses, instead of relying on static diagrams or written instructions.

Inference: The positioning is rooted in improving learning retention and clarity in movement instruction, especially for disciplines where visual feedback is critical but often delivered verbally.

There is no evidence of prior branding, marketing claims, or customer testimonials. The description is self-reported and unverified.

The author states that BodyMap is intended for movement instructors such as:

• Pole dance teachers
• Dance instructors
• Weightlifting coaches
• Aerial sports trainers

These users are described as those who currently give feedback verbally, often through video recordings, and struggle with students retaining the coaching after lessons.

Inference: The ICP appears to be individual or small group movement instructors working in niche disciplines where visual correction is essential but not well-supported by existing tools.

No evidence of segmentation beyond this broad category.

There is no evidence of a business model, pricing structure, monetization strategy, or revenue streams. The project is described as a hackathon submission with no indication that it has moved beyond prototype stage or is being offered for sale or use by others.

Inference: If this tool were to be commercialized, the author implies it would be used in one-on-one or small group instruction settings, but no pricing model or distribution plan is described.

The system is built using:

• React and TypeScript
• Vite for build tooling
• MediaPipe Pose Landmarker for pose detection
• Supabase for backend services (auth, storage)
• FFmpeg for video rendering
• AI tools like Codex for prototyping and implementation

The author notes that:

• The interface is responsive, adapting to both desktop and mobile workflows.
• Challenges included making pose detection editable, ensuring consistency between browser preview and exported MP4s, and handling mobile Safari issues.
• AI was used for prototyping, debugging, and accelerating repetitive tasks but was not fully reliable without clear sources of truth.

Inference: The technical stack is modern and appropriate for a web-based tool with media processing. However, the author also highlights limitations in AI use and edge-case handling, suggesting early-stage development.

There is no evidence of traction, customers, or adoption beyond the author’s own experience as an instructor. The project is described as a hackathon submission with no indication that it has been used by others or scaled beyond one person’s use case.

Inference: This is a prototype or proof-of-concept tool, not yet a product in active use or market-ready form.

The description does not mention any competitors, nor does it describe how BodyMap compares to existing tools for movement instruction or visual feedback. No market analysis or competitive positioning is provided.

Inference: The author has not identified or described existing solutions in this space, which may indicate either a lack of awareness or an unproven niche.

• No traction or customer data: The tool exists only as a prototype and has no evidence of real-world use.
• Single-person development: With only one team member (Steven Chu), there is limited capacity for scaling or iterating quickly.
• Unclear commercial viability: No pricing, monetization, or go-to-market strategy is evident.
• AI dependency risks: The author notes that AI tools were helpful but also introduced technical debt and unreliable results without clear sources of truth.
• Limited scope: The tool targets a narrow set of disciplines (pole dance, aerial, etc.) and may not generalize well.

1. What specific movement disciplines do you see as most suitable for this tool? Are there any that are harder to support?
2. Have you tested BodyMap with other instructors beyond yourself? If so, what feedback did they give?
3. How do you plan to scale beyond a single developer and prototype stage?
4. What is your vision for monetization or distribution if this were to become a product?
5. Are there any known edge cases or technical limitations that could prevent adoption in real-world settings?