This project was structured as a phased, two-year engagement, with Phase One dedicated to launching a Minimum Viable Product (MVP) in Spring 2022. This initial release allowed us to bring essential functionality to market quickly, enabling immediate feedback, early sales, and user engagement. Building on this foundation, we moved into Phase Two, which culminated in the full Version 1 (V1) launch in Fall 2023.
The MVP achieved its goal, validating the platform’s value and informing our development path toward a fully realized V1. With the V1 launch, we introduced a more precise speed measurement algorithm, a user-friendly interface, and a strengthened backend to ensure scalability and consistent performance.
To meet the project’s technical demands, the Scrapbox team applied advanced computer vision and machine learning techniques. A careful balance between automated processes and manual inputs ensured the highest accuracy in speed metrics, resulting in a platform that is efficient, scalable, and intuitive. This final product provides reliable, actionable insights that empower our client’s decision-making and drive results.
You can learn more about The UCReport and our max speed platform online at theucreport.com.
To create a platform capable of delivering reliable and precise player metrics, the Scrapbox team utilized an innovative combination of Python-based computer vision libraries, custom neural network models, and a uniquely crafted user interface. This blend of technology and design allowed us to achieve high accuracy in speed measurement, setting a new standard for assessing player performance in youth sports.
One of the most significant challenges in developing this platform was the inconsistent quality of game footage, a unique hurdle in our project. While computer vision has been employed to calculate speed in controlled environments, the Scrapbox team faced the added complexity of working with raw, low-quality footage recorded by non-professionals—often parents capturing high school games. These videos frequently include poor lighting, shaky camera movements, and limited resolution, making it difficult to obtain precise measurements using traditional methods. Additionally, inconsistencies like poorly painted field markings and obstructed player views added to the challenge, setting this project apart from standard applications of computer vision in sports analytics.
To address these challenges, we developed custom preprocessing algorithms to enhance the clarity and usability of low-quality video. Our solution includes automated stabilization, noise reduction, and adaptive resolution enhancement to counteract the limitations of non-professional footage. These preprocessing techniques ensure that the critical details needed for accurate player tracking remain intact, even when the video quality is suboptimal. This processing pipeline allows us to maintain high standards of accuracy in speed measurement, regardless of the film's initial quality.
We also adapted our neural network models to operate effectively in environments with diverse lighting conditions, camera angles, and field inconsistencies. By training our convolutional neural networks (CNNs) on a dataset reflective of these challenges—including footage from various high school games across different regions—we refined our model's ability to recognize and track players accurately despite the irregularities in the video. This adaptation to real-world conditions is a key differentiator of our platform, enabling it to deliver consistent results where other computer vision-based systems might struggle.
The final product stands out for its resilience and reliability in processing high school football footage—an area where other platforms may falter. By tackling the unique difficulties of low-quality, user-generated video, our team at Scrapbox has created a platform that isn’t just powerful but practical for real-world application. This capability to handle non-ideal footage without compromising accuracy provides our client, The UCReport, with a distinct advantage in the competitive landscape of sports analytics.
This project’s success showcases Scrapbox’s expertise in merging cutting-edge technology with real-world usability, making advanced performance analytics accessible and reliable, even in less-than-perfect conditions. Through innovative computer vision, custom neural networks, and a creative user interface, our solution delivers highly actionable insights, empowering recruiters to make data-backed decisions confidently, regardless of the quality of game footage they work with.
This project centered on driving revenue growth through high-impact, engaging email campaigns that help clients generate more income. To accomplish this, we developed Stimmy—an intuitive, AI-powered chat assistant built to provide real-time support for marketers. We also emphasized continuous improvement by integrating user feedback into each new feature release, ensuring that Stimmy evolves dynamically to meet the changing needs of its users.
Scrapbox integrated GPT-4 into Stimmy to provide intelligent, context-aware suggestions that enhance email content quality. Additionally, OCR technology enables Stimmy to analyze existing campaign materials, simplifying the generation of relevant and cohesive suggestions. We designed a scalable MVP, launched in March 2024, allowing Stimulate to test and refine Stimmy through real-world user feedback and application.
To build Stimmy, Scrapbox harnessed the power of OpenAI's GPT-4 alongside sophisticated Optical Character Recognition (OCR) technology to create a responsive, revenue-driven tool designed to maximize email campaign effectiveness. By leveraging these technologies, Stimmy offers marketers a unique and efficient way to generate impactful content tailored to their audience, ultimately driving increased engagement and revenue.
At the core of Stimmy's functionality is GPT-4, a powerful language model that enables intelligent, context-aware content generation. The AI is finely tuned to understand various campaign contexts, target demographics, and marketing strategies, allowing it to suggest email content that resonates with recipients. This integration ensures that every recommendation from Stimmy aligns with the brand’s tone and campaign goals, enabling marketers to craft messages that capture attention and drive action. By analyzing campaign parameters and historical engagement data, Stimmy delivers dynamic and relevant content ideas that boost open rates and conversions, making it a key asset for any revenue-focused email strategy.
OCR technology plays a critical role in Stimmy’s ability to incorporate and build upon existing campaign assets. By analyzing past campaign materials—such as images, PDFs, or scanned documents—Stimmy can extract key information and generate cohesive content suggestions that align with established campaign themes. This functionality allows marketers to seamlessly integrate past successes into new campaigns, maintaining brand consistency while saving time on content creation. This OCR-enhanced feature provides a significant edge for users, ensuring that Stimmy’s suggestions are relevant, informed, and aligned with ongoing marketing efforts.
The development process for Stimmy focused on scalability and adaptability, beginning with a Minimum Viable Product (MVP) launched in March 2024. This MVP enabled Stimulate, LLC to introduce Stimmy to a select group of users, gathering feedback on performance and usability in real-world scenarios. By prioritizing continuous feedback integration, we ensured that Stimmy’s feature set evolves in direct response to user needs. Each iteration has been informed by hands-on insights from marketers, allowing us to fine-tune the tool for intuitive interaction and maximum effectiveness.
Scrapbox designed Stimmy’s architecture to support future enhancements, from advanced analytics to personalized user settings. This scalable foundation ensures that as users’ needs evolve, Stimmy can adapt, offering increasingly tailored insights and integrations. In providing Stimulate’s clients with a tool that evolves with their business needs, Stimmy stands out as a forward-thinking solution in the competitive landscape of retention marketing.
With Stimmy, Scrapbox has delivered a comprehensive, AI-powered assistant that enables marketers to optimize email campaigns with unprecedented precision and efficiency. Combining the advanced content generation capabilities of GPT-4 with the strategic insights from OCR, Stimmy empowers marketers to maximize engagement and revenue, solidifying its role as an invaluable tool in modern retention marketing.
.jpg)
The EndorseMate platform empowers college athletes to leverage their NIL (name, image, and likeness) rights by connecting them directly with brands for sponsorship opportunities. To achieve this, we developed a marketplace that facilitates smooth negotiation and transaction processes for sponsorship deals. Our approach prioritized launching a scalable MVP quickly to kickstart user acquisition and engage stakeholders in meaningful conversations around the platform’s potential. The project was featured in Bentley University's Newsroom: bentley.edu/news/getting-game.
The NIL marketplace was built using React and Next.js, ensuring a responsive and high-performance user experience. To protect user data, we integrated secure authentication through Auth0, enhancing overall platform security. In just four months, we delivered a functional MVP, which allowed EndorseMate to successfully attract over 150 student-athletes and initiate brand partnerships.
The MVP launch was a great success, allowing Lucas and the EndorseMate team to begin conversations with universities, brands, and potential investors.
This project aimed to make trademark registration more accessible by simplifying the process for users and removing the need for legal intervention. To enhance accuracy, we incorporated AI-powered error detection using large language models (LLMs) to analyze inputs in real-time and catch common mistakes. Additionally, we designed the platform to be scalable, enabling WizardIP to license the technology to legal firms, allowing them to automate and streamline their own registration practices.
We implemented GPT-based LLMs to provide users with real-time guidance throughout the trademark registration process, ensuring a smooth and error-resistant experience. Built with NextJS and Elasticsearch, the platform offers fast and efficient data processing and retrieval, enhancing overall user experience. Designed as licensable technology, the platform serves both direct consumer needs and enables enterprise partnerships with legal firms, allowing WizardIP to expand its reach and impact in the legal tech space.
WizardIP’s platform has achieved nationwide reach, offering trademark services to users across the U.S. By reducing legal barriers, it makes trademark registration accessible to individuals without legal expertise. The Scrapbox team continues to work closely with WizardIP, expanding features and refining the platform to meet evolving user needs.
.png)
PKS’s existing software suite, an on-premises system developed over 20 years ago, has been instrumental to their operations but lacks the scalability and functionality required to meet the demands of today’s environment. Recognizing the need for a modern solution, PKS engaged Scrapbox to design and build an entirely new software platform that not only replaces their legacy system but enhances it, with cloud migration and next-generation capabilities at its core.
To ensure a successful transformation, our team has taken a holistic approach, led by dedicated business analysts who are documenting PKS’s processes in detail. This comprehensive documentation phase allows us to understand each facet of PKS’s business operations and identify critical areas for improvement. Our architects have designed a new system from the ground up, specifically tailored to PKS’s needs and optimized for efficiency, scalability, and adaptability.
Scrapbox’s engineering team is building the entire platform, implementing modern software engineering practices and leveraging cutting-edge technologies to create a robust, user-friendly system. In addition, we are leading a full cloud migration, moving PKS’s operations from an on-premises infrastructure to a scalable, secure cloud environment. This migration ensures flexibility, improved data accessibility, and reduced overhead costs, positioning PKS to respond dynamically to future needs and growth opportunities.
The newly developed platform is set to drive significant efficiency gains by streamlining PKS’s core business functions, minimizing the need for manual processes, and enabling smoother workflows across the organization. Through cloud migration, PKS will also realize substantial cost savings by reducing on-premises maintenance and infrastructure expenses, directly improving their bottom line. The cloud-based design supports scalability, providing PKS with a flexible foundation that can expand and adapt seamlessly as their business grows. Additionally, the redesigned user interface offers a modern, intuitive experience that enhances ease of use for PKS’s team, making day-to-day operations faster and more efficient.
Through this transformative partnership, Scrapbox is empowering PKS Associates to operate at peak efficiency, adapt to evolving needs, and prepare for sustained growth well into the future. With a technology infrastructure tailored to their unique needs, PKS is now positioned to achieve its vision for continued success and leadership in the industry.
%201.png)
.png)
.png)
