CabVector

Company: CabVector

Self-reported basis: The description is entirely self-reported by the project authors and unverified. No third-party corroboration exists.

Commercial due-diligence read: CabVector appears to be a proof-of-concept full-stack web application designed to optimize taxi dispatch during NYC subway disruptions using AI-driven logic, live transit data, and geospatial mapping. It is not evidenced to have any revenue, customers or traction beyond the hackathon submission. The single most important open question is whether the system can scale beyond a demo to real-world deployment with actual taxis and city coordination.

The description states that CabVector is a full-stack web application built to manage taxi staging during NYC subway disruptions. It uses:

• FastAPI for backend logic (state management, scoring, safety workflows)
• Next.js for frontend dashboard
• Leaflet.js and CARTO for map visualization
• Integrations with MTA, NYC DOT, OpenAI, Groq APIs
• A deterministic workflow: Fleet proposal → Traffic validation → Approved dispatch

It is described as a system that evaluates taxi dispatches using two criteria:

• L-Score > 70
• Congestion Index ≤ 0.7

The system is said to be governed by a strict, deterministic workflow and includes fallback mechanisms for flaky public data feeds.

Inference: The product is a prototype or hackathon demo, not a production-ready service. It is not evidenced to have real-world taxi integration or live dispatch capabilities beyond the demo environment.

The description states that CabVector aims to solve the problem of “how can we proactively guide taxis toward stranded passengers without turning the surrounding streets into a parking lot?”

It positions itself as a solution for transit disruptions in NYC, using AI and real-time data to optimize taxi staging zones.

Inference: The positioning is centered on solving a specific urban mobility challenge. It claims to be proactive rather than reactive, but there is no evidence of prior deployment or adoption by any city or taxi operator.

The description does not name specific customer types or personas. However, it implies that the system targets:

• NYC taxi operators
• City traffic management authorities
• MTA or other transit agencies (via integration)

It is described as solving a problem for stranded passengers and city gridlock.

Inference: The ICP likely includes local transportation stakeholders, but no explicit customer segmentation or persona data is provided.

The description does not mention any pricing model, monetization strategy, or business model. It is framed as a hackathon project with no indication of commercial intent or revenue streams.

Inference: No evidence of a business model or pricing structure exists in the self-reported description.

The system is built using:

• Backend: FastAPI
• Frontend: Next.js, React
• Mapping: Leaflet.js, CARTO
• Data sources: MTA, NYC DOT, OpenAI, Groq, OpenStreetMap
• Tools: Codex (GPT-5.6), Pydantic, TypeScript, REST APIs, Server-Sent Events

It includes:

• Deterministic workflow logic
• Fallback mechanisms for API failures
• Live health indicators
• Shared contracts to maintain synchronization
• Fixture data for demo stability

Inference: The technical stack is modern and full-stack. It shows engineering sophistication but lacks evidence of production deployment or live integration.

The project was submitted to the OpenAI 2026 hackathon on Devpost. No revenue, customer adoption, or traction data are provided beyond this.

Inference: The system is at a demo or prototype stage. There is no evidence of real-world usage or operational deployment.

The description does not mention competitors or similar products. It is framed as solving a specific urban mobility problem without reference to existing solutions in the market.

Inference: No competitive landscape is described, and there is no evidence of prior market analysis or product differentiation.

• Unproven scalability: The system is described as a hackathon demo with no evidence of real-world deployment.
• No commercial viability: No pricing, monetization or customer model is evident.
• Limited data integration: Reliance on public APIs that are known to be unreliable.
• No traction or adoption: No customers, revenue or usage metrics are reported.
• AI dependency without operational safeguards: The system uses AI suggestions but enforces strict rules — a potentially risky balance.

Inference: The project is not evidenced to have moved beyond the prototype stage. It lacks commercial viability and real-world validation.

1. What is the current status of taxi operator or city stakeholder engagement?
2. Has the system been tested in a live NYC transit disruption scenario?
3. Are there any partnerships or pilot programs with taxi companies or city agencies?
4. How does the system handle edge cases, such as multiple simultaneous disruptions?
5. What are the technical and legal barriers to scaling this beyond a demo?
6. Is there a plan for monetization or long-term sustainability?