CoolWalk

Company: CoolWalk

Self-reported basis: The description is entirely self-reported by the author, with no independent verification.

Commercial due-diligence read: CoolWalk is a proof-of-concept walking navigation app that uses geospatial modeling and AI to compute shade-aware routes in Manhattan. It is not evidenced to have any revenue, customers or traction. The project appears to be a hackathon submission with no commercialization plan evident. The single most important open question is whether the author intends to build a product beyond this prototype.

The description states that CoolWalk is a walking navigation app for Manhattan that compares two routes side-by-side: one fastest and one coolest, based on real building shadows, tree canopy, and live weather data. It uses GPT-5.6 for natural language interpretation of user preferences and integrates with Google Cloud and OpenStreetMap data.

Evidence:

• "CoolWalk exists to fix that specific gap: a walking navigation app that compares your fastest route against your coolest one"
• "The entire project — every line of code, every data pipeline, every bug fix — was built through Codex running GPT-5.6"

Inference:

• The product is described as a geospatial routing tool with AI-powered preference parsing.

CoolWalk positions itself as a solution to the lack of shade-aware navigation in mainstream apps like Google Maps or Apple Maps. It claims to offer physically modeled, real-time routing that accounts for environmental factors such as sun position, building shadows, and tree canopy.

Evidence:

• "Google Maps, Apple Maps, every mainstream navigation app — they all optimize for exactly one thing: speed. None of them know where the shade is, and none of them care."
• "CoolWalk exists to fix that specific gap"
• "a walking navigation app that compares your fastest route against your coolest one, using real building shadows, real tree canopy, and live weather"

Inference:

• The positioning is a niche solution for heat-aware urban navigation.

The description does not state a defined customer segment or ideal customer profile (ICP). It implies the app is for anyone walking in Manhattan who might be concerned about heat exposure, such as people with asthma, elderly individuals, or those in rush situations.

Evidence:

• "You describe your situation in plain language — 'I'm walking with my grandmother,' 'I'm in a rush,' 'I have asthma and it's a bad air quality day'"
• No explicit ICP defined

There is no evidence of a business model or pricing structure. The project is described as a hackathon submission without any indication of monetization strategy.

Evidence:

• "Everything above is the authors' own account. It is not independently verified, and no revenue, customer or traction data is available beyond what they state."

The description includes detailed technical architecture, including use of suncalc, NYC building footprints, LiDAR-derived canopy polygons, OpenStreetMap, weighted Dijkstra routing, and GPT-5.6 for preference parsing.

Evidence:

• "Sun position — suncalc, validated against real published NYC sunrise/sunset/solar-noon times"
• "Building shadow geometry — real height and footprint data for all 45,209 Manhattan building footprints"
• "Tree canopy — 398,279 LiDAR-derived canopy polygons"
• "Routing — a 318,002-edge citywide graph"
• "Natural-language preferences — GPT-5.6 parses free text into routing weights"

Inference:

• The technical implementation is described as complex and geospatially accurate.

There is no evidence of traction, customers, or product maturity beyond the hackathon submission. No revenue, user base, or adoption metrics are provided.

Evidence:

• "Everything above is the authors' own account. It is not independently verified, and no revenue, customer or traction data is available beyond what they state."
• "This project was submitted to the OpenAI 2026 hackathon on Devpost."

The description does not mention any competitors. The author states that mainstream navigation apps do not consider shade, but no specific competitive landscape is described.

Evidence:

• "Google Maps, Apple Maps, every mainstream navigation app — they all optimize for exactly one thing: speed. None of them know where the shade is, and none of them care."

Key risks include:

1. The project is a hackathon submission with no commercialization plan.
2. No evidence of revenue or customer traction.
3. Heavy reliance on AI coding tools (Codex/GPT-5.6) for development, which may not scale or be reliable for production use.
4. Lack of clear monetization strategy.

Evidence:

• "This project was submitted to the OpenAI 2026 hackathon on Devpost."
• "No revenue, customer or traction data is available beyond what they state."

1. What is your plan for commercializing this product beyond the hackathon?
2. Have you considered how to scale this geospatial pipeline beyond Manhattan?
3. How do you intend to monetize this app, if at all?
4. What are the technical and operational challenges of moving from a prototype to a production-grade service?
5. Are there any legal or regulatory considerations for using OpenStreetMap and NYC data?