Initiative details
The main challenge addressed by this practice is the traditional barrier to entry for deep-tech innovation: the need for large, specialized, and expensive development teams. This often slows down a project's ability to adapt and innovate, especially for mission-driven initiatives with limited initial resources.
Initiative date
Who was/is your target audience?
Policy makers
Public authorities
Company employees
Fleet operators
Car drivers
Car drivers – professional
Educational staff
Emergency services
Others
Topic
Improve vehicles and infrastructure
Knowledge building and sharing
Organisation details
The RoRiMo Project
Enterprise
Hungary
Eindhoven
Contact name
Andras Varga
Telephone number
+36706229933
andras.varga@rorimo.com
Website link
Project activities
If you work together with external partners, list the most important partners and briefly describe their role.
Our primary "external" partner in this specific practice is the AI itself. We treat it as a collaborative entity, leveraging platforms like Google's Gemini API to serve as our 'colleague' for code generation and problem-solving. This human-machine partnership is the cornerstone of our innovation model.
In parallel, our founding team has recently expanded with a technical hardware specialist who co-develops our prototypes using this methodology. We are also in active dialogue with innovation hubs like the High Tech Campus in Eindhoven to build a network of academic and research partners interested in exploring and co-developing this new model of agile, AI-assisted innovation.
In parallel, our founding team has recently expanded with a technical hardware specialist who co-develops our prototypes using this methodology. We are also in active dialogue with innovation hubs like the High Tech Campus in Eindhoven to build a network of academic and research partners interested in exploring and co-developing this new model of agile, AI-assisted innovation.
Please describe the project activities you carried/are carrying out and the time period over which these were implemented.
We have implemented a unique human-machine collaborative process. Our founder, a non-coder with deep domain expertise, sets the strategic vision, ethical boundaries, and functional requirements. An AI partner is then utilized as a tool and a "colleague" for tasks like code generation, data analysis, debugging, and even hardware simulation. This allows our small, core team to achieve a development velocity and technical depth comparable to much larger organizations.
In terms of implementation, what worked well and what challenges did you need to overcome?
The synergy between human domain expertise and AI's execution capability has worked incredibly well. It has allowed us to build a fully proprietary, complex backend/frontend platform in record time. The main challenge was developing a new workflow and mindset where the human's role shifts from "doing" to "directing, validating, and integrating."
Evaluation
Please summarise how you have evaluated the initiative’s impact (e.g. social media reach, survey, feedback forms, statistics).
The impact of this methodology is evaluated through a combination of quantitative and qualitative measures.
Quantitative Evaluation: We benchmark our development timeline and the resulting platform's complexity against industry standards for similarly scoped projects. This provides a clear measure of the radical acceleration achieved.
Qualitative Evaluation: The successful creation of a market-ready, proprietary platform with a minimal core team serves as the primary validation.
Statistical Validation: The output of this practice—the RoRiMo system—is evaluated through controlled tests. Statistics from our MVP tests (e.g., the >90% reduction in high-risk driving behaviors) serve as direct proof of the methodology's effectiveness in producing an impactful road safety solution.
Quantitative Evaluation: We benchmark our development timeline and the resulting platform's complexity against industry standards for similarly scoped projects. This provides a clear measure of the radical acceleration achieved.
Qualitative Evaluation: The successful creation of a market-ready, proprietary platform with a minimal core team serves as the primary validation.
Statistical Validation: The output of this practice—the RoRiMo system—is evaluated through controlled tests. Statistics from our MVP tests (e.g., the >90% reduction in high-risk driving behaviors) serve as direct proof of the methodology's effectiveness in producing an impactful road safety solution.
What has been the effect of the activities?
The effect is a radical acceleration of our development cycle and the successful creation of a sophisticated, market-ready platform with a minimal core team. This practice has directly enabled the development of the RoRiMo system, which, in its MVP stage, has already demonstrated the ability to reduce high-risk driving behaviors by over 90% in controlled tests. The impact is currently local to our pilot project but has clear international potential.
Please briefly explain why your initiative is a good example of improving road safety.
This practice is a game-changer because it democratizes the creation of advanced safety technology. It is particularly effective and efficient because it dramatically lowers the financial and human resource barriers to innovation. It proves that a deep understanding of the problem (road safety) combined with a strategic partnership with AI can create world-class solutions, breaking the dependency on massive R&D budgets. It complements other activities by enabling more diverse actors (non-profits, public bodies, smaller enterprises) to become active creators in the safety ecosystem.
How have you shared information about your project and its results?
This methodology is the foundation of our internal work culture. We are documenting the process and plan to share our findings and best practices through technical blog posts on roadriskmonitor.com and in dialogues with academic and innovation partners to inspire a new model of human-AI collaboration. The results of the systems built with this methodology are shared via our public-facing infographic and will be the subject of future case studies and pilot project reports.