Bilal Raza@billy_prg

"Predict locust swarm movements using satellite data, deploy drones for targeted intervention, safeguarding agriculture and communities." "Our project aims to detect locust swarms preemptively, utilizing satellite data to predict their path towards cities and vegetation. By analyzing factors such as weather patterns and locust behavior, our system issues alerts to control centers and deploys drones for targeted intervention. Additionally, the system facilitates informed decision-making by providing data for potential aerial interventions. With an automated drone launch option, our solution ensures swift and effective response to locust swarm threats, safeguarding agricultural resources and communities."

The development of a Prompt Scoring Engine aims to enhance the output quality of Large Language Models (LLMs) and improve user experience. This engine evaluates and scores prompts based on various criteria to optimize the responses generated by LLMs. The implementation of this technology addresses key issues related to the effectiveness of AI models, the clarity of project presentations, business value, and originality. The project began with an extensive research phase, focusing on methods to evaluate prompts and develop criteria for their assessment. A rubric was created to score prompts from 1 (worst) to 7 (best). Following this, a configuration file for a custom GPT model was developed, which utilized the rubric to evaluate prompts and their inputs. This configuration provided a structured approach to identify areas for improvement and generate requirements for enhancing prompt quality. The core implementation involved creating a scoring engine that interacts with users by prompting them to input their original prompts and resulting outputs. The engine evaluates these inputs, scores them based on the established rubric, and suggests improvements. Users are then given the opportunity to try the new, optimized prompts and evaluate the results, creating a continuous feedback loop that refines the prompt quality over time. The Prompt Scoring Engine offers significant benefits, including enhanced output quality through advanced natural language processing techniques, improved user experience with more relevant and coherent responses, and a transparent, objective evaluation framework. Additionally, it serves as an educational tool, helping users understand and craft better prompts. This strategic initiative not only addresses critical issues in AI model effectiveness but also drives innovation and growth in the AI market by ensuring high-quality, original, and clear outputs.

The Lokahi Precision Care Portal unifies patient care, monitoring, and billing by leveraging synthetic data, wearables, and agentic technology. This innovative solution delivers personalized insights and remote care management, with a specific focus on the breast cancer use case. The initiative aims to modernize medical insurance programs and provide seamless, patient-centered solutions by ensuring new technologies are fully integrated rather than treated as add-ons. Using Power B I we analyzed the Lokahi insurance database to facilitate this seamless integration, laying the foundation for a holistic approach to precision care. The project emphasizes addressing challenges unique to breast cancer patients, such as cognitive conditions like "Chemo Brain." It incorporates several data streams—Wearable Data, Breast Cancer Data, and a comprehensive Treatment Model—to deliver tailored insights. These tools work in harmony with the Patient Talk feature, which enhances engagement by providing real-time, personalized guidance, fostering trust, and enabling timely interventions through an agentic Clinical Decision Support System (CDSS). Together, these elements improve patient outcomes and optimize healthcare delivery. By combining cutting-edge technology and accessibility, the Lokahi Precision Care Portal redefines healthcare with an integrated solution that unifies care and billing while alleviating the strain on Hawaii's medical system. Special thanks to the team: Ahmad, Bilal, Amanullah, Reema, and Anjalee.