david lively@DavidLively

Project Proposal The project's objective is to transform reading for children with learning disabilities using a Generative AI application built on the Clarifai platform, creating a "Branching Reading Adventure." It's designed to assist children with Visual Impairment, Dyslexia, ADHD, Auditory Processing Disorder, Language Disorders, and Cognitive Disabilities. Core Features: Interactive Story Creation: Utilizing CrewAI, this application turns a child's ideas into personalized learning adventures, encouraging them to become story creators. Rich Story Elements: Using Clarifai's AI, the app generates diverse story elements (images, audio, text) to create an immersive, multi-sensory reading experience. Dynamic Story Branching: The app integrates Clarifai's object identification and Chat Vision GPT-4 for real-time, interactive story alterations, enhancing engagement. Adaptive Learning Loops: It continuously loops through stories, allowing children to learn at their own pace and in a relaxed environment. Progress Evaluation Tools: For the future we plan to incorporate Clarifai's RAG system, to include tools for educators and caregivers to track progress and identify learning needs. Project Impact: "Branching Reading Adventure" aims to foster an inclusive and adaptable learning space, offering new possibilities for children limited by traditional learning methods. It focuses on both educational and emotional development, enhancing self-confidence in children with learning disabilities. Conclusion: Aligned with the hackathon's theme 'Empowering Learning Through Technology', this proposal represents a significant step towards inclusive education. The team is enthusiastic about its potential impact and looks forward to developing this innovative application.

Long Description: At the heart of our vision is the belief that generative AI technology has revolutionized the film industry, opening doors for virtually anyone to step into the role of a movie producer. Our project in this Hackathon aims to validate this concept by crafting a concise, 35-second film "composed of shorts," leveraging cutting-edge generative AI tools, namely Custom GPT and Stable Video Diffusion, in line with the competition's guidelines. Our methodology encompassed four distinct phases: Utilizing our Script Writing Custom GPT to generate the film script and accompanying images. Employing Eleven Labs for the audio narration of our script. Transforming the generated images into brief, 5-second video segments using a Stable Diffusion Image 2 Video XT tool from HuggingFace. Assembling these segments in Filmora to produce a cohesive 35-second film, complete with narration and sound effects. Overall, the execution was remarkably smooth. We navigated technical hurdles with ease, and our strategy of utilizing autonomous agents for script and image creation proved to be a groundbreaking approach for swiftly developing scripts for short films.

This project introduces an AI-powered stock portfolio management system, designed for optimizing investments based on individual risk profiles. It leverages three AI agents to create, optimize, and fine-tune a risk-adjusted portfolio. Key Components: Custom GPT: Tailors portfolios to four risk categories: Conservative, Growth, Balanced, Aggressive. Optimization: Uses Metrics. AI Fine-Tuning: Employs 3 CrewAI agents for portfolio finetuning adjustments. Features: Creates and adjusts a 10-stock portfolio. AI-driven insights for informed investment decisions. Technologies Used: Custom GPT, Gemini, LangChain, CrewAI, and Hugging Face. Conclusion: This system blends AI innovation with strategic investment management, offering personalized, dynamic portfolio solutions.

The integration of Mixtral for authentic human conversations has proven to be remarkably successful. In an upcoming version, we plan to refine the sequencing to more accurately mimic real group dynamics. Additionally, we aim to introduce a human participant to interact within this digital environment. A pivotal realization emerged: Mixtral's utility extends beyond patient support; it's a valuable tool for therapists to enhance their sessions and gather insightful statistics. Our programming “aha” moment was the use of Steps to create a final report and the use sentiment analysis to grade the session and offer feedback on how to make it better in the future. The societal benefits of Mixtral are multifaceted: Firstly, it establishes a secure and nonjudgmental space for discussing sensitive matters. Secondly, it furnishes therapists with a feedback mechanism to refine their practice. Lastly, it generates vital statistics, often required for governmental funding, through methods like sentiment analysis.

Our philosophy is to fix and add, not cut. We approach DOGE with abundance, leveraging AI as a one-to-many solution that addresses problems with innovative, unexpected solutions. Reimagining Learning with AI By incorporating agentics—autonomous AI agents—learning evolves into interactive and immersive experiences: Enhanced Learning: Fictitious companies come to life, engaging learners in dynamic discussions. Software Integration: Agentics assist in creating functional software, enabling learners to produce real-world products. Addressing Education’s Challenges Education is broken: costly, impractical, and uncreative. AI-driven agentic scrum teams offer solutions by emphasizing collaboration, practical skills, and real-world impact. Project Workflow The project workflow consisted of three main steps: Building a JavaScript Course Player: The foundation for an interactive course experience. Creating the Grok Agentic System: A configuration file informed Grok where agentics were located within the course. This included a Grok Agentic Dialog Team, represented by the agentic agents: Zoe Kim, Software Engineer Alex Patel, DevOps Engineer Jack Dawson, Cloud Architect Designing the Grok Query System: This system accompanies the learner throughout the course, providing rich, interactive conversations and coding examples. Transformative Approach Agentic teams foster hands-on learning where students actively solve challenges, such as designing efficient housing. They empower learners to leave the classroom with deployable skills and creative solutions. Acknowledgments Special thanks to the team: Jaweria, Amanullah, ALI, Abeera, and Davy.