Road Speed

What the company appears to be: Road Speed is an iOS app built by a single developer (Paul Ledger) that uses video analysis and computer vision to estimate vehicle speeds from roadside footage. It was submitted as a project for the OpenAI 2026 hackathon.

What changed: The author states that the app evolved from an early experiment into a working iOS application during the hackathon period, incorporating features like timestamp-accurate tracking, perspective-aware calibration, and evidence export.

The single most important open question: Is there any evidence of actual usage or traction beyond the developer's own testing and submission to a hackathon?

Note: This analysis is based entirely on the self-reported description provided by the author. No independent verification, revenue data, customer information, or traction metrics are available.

The description states that Road Speed is an iOS app designed to:

• Record or import roadside video
• Estimate vehicle speeds using frame-by-frame analysis
• Use actual timestamps of video frames for timing calculations
• Calibrate road width via a top-down view
• Track vehicles using computer vision and Core ML
• Show vehicle contact trails for visual evidence
• Export supporting video evidence with speed estimates

The app uses Swift, SwiftUI, and various Apple frameworks including AVFoundation, CoreML, and MapKit. It leverages Codex with GPT-5.6 to assist in development.

Inference: The product is a proof-of-concept tool built for personal use and hackathon submission; it does not appear to be a commercial product or have any revenue-generating features.

The author claims that Road Speed helps document speeding issues by providing:

• Timestamp-accurate speed estimates
• Visual evidence of vehicle movement
• Perspective-aware calibration
• Exportable video evidence

It is positioned as a tool to support community road safety reporting, not as certified enforcement equipment.

Inference: The app's positioning has evolved from a personal problem-solving effort into a more structured tool during the hackathon, but it remains focused on documentation rather than enforcement or commercial use.

The description states that the app was developed for residents in rural areas who want to document speeding concerns. It is intended for individuals or community groups seeking better evidence to support requests for traffic monitoring.

Inference: The target customer is likely a niche audience of private citizens or small community organizations, not businesses or government agencies. No specific ICP (Ideal Customer Profile) is defined beyond this general use case.

There is no evidence of any business model or pricing structure in the description.

Finding: Not evidenced.

The app was built using:

• Swift and SwiftUI
• AVFoundation, AVKit, CoreML, CoreImage, CoreMedia, CoreVideo, MapKit
• Codex with GPT-5.6 for development assistance
• Video import and high-frame-rate recording capabilities
• Frame-by-frame analysis with timestamp accuracy
• Perspective-aware calibration using top-down view
• Vehicle tracking via vision and Core ML
• Wheel-position tracking as fallback

Inference: The technical stack suggests a native iOS application built with modern Apple technologies, but no evidence of production deployment or scalability beyond the developer's own use.

The description indicates that the app was developed during a hackathon (OpenAI 2026) and evolved from an early experiment into a working prototype. The author mentions:

• Adding features like evidence export, saved calibration, and improved summaries
• Testing against sample footage
• Using regression tests

However, there is no mention of actual users, downloads, or adoption beyond the developer's own testing.

Finding: Not evidenced.

No competitive landscape or market analysis is provided in the description. The author does not reference existing tools or competitors for roadside speed estimation or video-based vehicle tracking.

Finding: Not evidenced.

• The app is described as a hackathon project with no commercial traction.
• It is built by a single developer (1-person team), which raises questions about scalability and long-term maintenance.
• The use of AI tools like Codex for development may indicate limited technical depth or reliance on automation.
• There is no evidence of revenue, customers, or product-market fit beyond the author’s own testing.

Inference: The app lacks commercial viability indicators and appears to be a personal tool with no clear path to monetization or widespread adoption.

1. What is the actual utility of this tool in real-world situations?
2. Has there been any independent testing or validation of the speed estimation accuracy?
3. Are there plans for monetization or commercial use beyond personal documentation?
4. How does the app handle edge cases like poor lighting, occlusion, or varying vehicle types?
5. Is there any intention to expand beyond iOS or integrate with other platforms?