An AI-powered assistant that extracts, classifies, and analyzes financial data from Excel files and PDFs to generate clean financial statements, dashboards, and exportable reports — all without manual formatting. Long Description Our MVP is an AI-powered Financial Analysis Assistant designed to automate the most time-consuming parts of financial reporting. Users can upload trial balances in Excel or Annual Reports in PDF format. The assistant then: Extracts financial data using intelligent parsing of unstructured and semi-structured documents. Classifies each data point into standardized IFRS categories using a dynamic mapping engine, tailored to balance sheets, income statements, and cash flows. Displays results through a structured and interactive interface where users can review mappings, validate outputs, and navigate statements. Exports clean Excel files, ready-to-use dashboards, and presentation-ready PowerPoint slides — significantly reducing the time analysts spend on formatting and restructuring. The MVP also includes a review layer where users can investigate discrepancies, reconcile subtotals, and adjust mappings with the help of a chat-based assistant. The goal: Let finance professionals focus on insight and decision-making — not formatting spreadsheets.

ContractIQ is an intelligent legal document assistant designed to streamline the contract analysis workflow using AI. The app allows users to upload contract files (e.g., PDFs or DOCX), from which it automatically extracts key legal clauses using natural language processing (NLP). These clauses are stored in a vector database (Zilliz/Milvus) using embeddings for semantic search. When a user wants to check if a certain clause exists or if similar clauses have been previously stored, the app uses a similarity search algorithm to return the most relevant results. This eliminates the need to manually comb through long legal documents. The app also integrates a language model (via Novita AI API) to answer clause-related queries, generate summaries, or enhance explanations, making it not just a retrieval tool but also a smart contract assistant.

RiskRadar is a cutting-edge application designed for business professionals, startups, and investors. It leverages real-time news sources to identify potential business risks and opportunities, with a focus on topics such as natural disasters, market trends, and economic shifts. Powered by Groq LLaMA3-70B, SerpAPI, and Plotly, this tool provides accurate risk analysis and strategic insights through advanced natural language processing (NLP) models. It also offers location-based risk mapping and visualizations for easy decision-making. The app provides actionable insights by analyzing news headlines and offering strategies for capitalizing on market shifts. With the integration of SerpAPI, it fetches the latest real-time news, and with Groq's AI capabilities, it generates analysis and predictions on potential risks and opportunities for businesses in real time.

TestFastTrack is an innovative app designed to enhance IELTS test preparation by providing immediate, intuitive feedback. Traditional learning methods often leave users struggling to understand their mistakes; TestFastTrack addresses this by utilizing real IELTS test passages and images to create a clear feedback loop. Users receive instant, detailed explanations for their errors, facilitating actionable learning rather than rote memorization. The app’s visual approach and progress tracking empower learners to engage with the material meaningfully and monitor their improvement over time. With over 3.5 million IELTS test-takers annually, TestFastTrack meets the growing demand for efficient, personalized learning tools.

A tool for large enterprises that allows distributed teams to collaborate on coding projects with AI-enhanced support. Replit provides the cloud-based environment for real-time collaboration, Cursor optimizes team efficiency with predictive code generation and error detection, and Claude acts as a Tech Lead, helping with code reviews, suggesting optimizations based on the team's previous code, and ensuring the team follows best practices. Multiple developers work together in Replit, with Cursor helping teams refactor, debug, and enhance their code. Claude can provide high-level oversight, such as suggesting improvements based on the overall codebase, offering advice on architecture or optimization, and ensuring security and compliance protocols are followed. This tool would significantly enhance team productivity and code quality, ensuring consistency and efficiency across large development projects. It would be especially valuable for enterprises that rely on remote or distributed teams.

We present a general biological research agent designed to accelerate discoveries in biology, medicine, and cancer research. Our agent combines a powerful Python-based backend with an intuitive chatbot front end, creating a seamless interface for researchers to interact with complex computational tools using natural language. This project demonstrates how artificial intelligence can streamline research processes, from literature mining to data analysis and hypothesis generation. By integrating advanced natural language processing models and machine learning algorithms, the agent assists researchers in navigating vast scientific literature and data. The platform can process large datasets, extract pertinent information, and provide context-aware responses to complex queries. The Python backend leverages robust computational libraries, ensuring efficient data handling and analysis, while the chatbot interface UI allows users to engage conversationally, lowering the barrier to entry for those without extensive technical expertise. One key feature is advanced literature mining; the agent performs comprehensive searches across databases like PubMed Central [1] and arXiv [2]. Utilizing natural language processing models, it extracts key findings, summarizes articles, and identifies emerging trends, helping researchers stay updated with the latest developments. Our general biological research agent represents a significant advancement in integrating artificial intelligence into biomedical research. We are excited about the possibilities this tool presents and look forward to refining it further, integrating new features, and collaborating with the research community to maximize its impact. [1] PubMed Central, https://www.ncbi.nlm.nih.gov/pmc/ [2] arXiv, https://arxiv.org/.

We designed four agents to automate the SDLC. These were: Requirements Agent: Understand requirements from requirements doc Design Agent: Create high level design doc Software Development Agent: Generate codebase to build PoC (small project) Code Test Agent: Generate code tests The workflow steps we followed were as follows: a. Requirements Gathering Task: Extract key requirements from a document. Goal: Create a concise summary of the CRM system's required features. Outcome: Defines the project scope (authentication, CRUD operations, task management, reporting). b. High-Level System Design Task: Design the architecture of the CRM system. Diagrams Generated: Use Case Diagram Class Diagram Entity-Relationship Diagram (ERD) UI Design for Dashboard Outcome: A document detailing the architecture, components, and visual diagrams of the system. c. Code Generation Task: Develop the Code for the system. Goal: Create functional code that implements core features. Outcome: Working code implementing authentication, database operations, and reporting. d. Code Testing Task: Run test cases to verify code functionality. Goal: Ensure the system meets the requirements and works as expected. Outcome: A detailed test report highlighting results and potential issues. Future Work could include: Improvements in Design Diagrams: Explore more AI-driven tools for automated generation of detailed design diagrams. Customization: Enable more advanced configurations for tasks such as adding new agents or expanding CRM functionality. Deployment: Plan for deployment of the final CRM system in a production environment. We also considered building an agentic workflow for MLOps, but ultimately decided on the SDLC.

The CodeBlast Dream Catcher proposes an innovative approach to searching multidimensional space for knowledge based on the following eight principles: 1. An "all possible combinations space" exists in a multidimensional space where knowledge is discovered, not created. 2. This multidimensional space is best searched with LLMs using goals, as goals carry the recipes for accomplishing them. 3. There exists a multidimensional "all possible" Codestral goal space consisting of interconnected goals resembling a graph. 4. This multidimensional goals space can best be searched by remapping it to the 2D Infinite Canvas proposed in the LabLab.ai Build Your Business Startup Hackathon's "Navigating the Infinite Plane". 5. The infinite canvas can be created using a 50256 base number system derived from the GPT-2 tokenization labels. 6. To avoid the costly computational expense of base number conversion, hidden and unhidden states are created in the 2D infinite plane. 7. These hidden and unhidden states correspond to the conscious and unconscious mind, proposing that the human brain uses a similar mechanism to avoid the heavy cost of base number conversion. 8. Thus, searching for knowledge becomes a simple mapping problem in 2D and 1D space in both hidden and unhidden states. Business Value: The CodeBlast Dream Catcher approach offers significant business value through the following benefits: Efficient Knowledge Discovery Resource Optimization Enhanced Decision-Making Scalability Flexibility Strategic Advantage The CodeBlast Dream Catcher approach redefines knowledge discovery by leveraging LLMs and innovative mapping techniques to efficiently explore multidimensional spaces. By optimizing resources, enhancing decision-making, and offering scalability and flexibility, it provides a strategic advantage, making it a valuable tool for businesses aiming to lead in advanced AI knowledge discovery.

Welcome to our AI App Solution! This comprehensive suite offers tools for medical analysis and interaction, including Cataract Analyzer, Glaucoma Analyzer, an embedded chatbot, and an SQLite database for efficient data management. The Cataract Analyzer and Glaucoma Analyzer use advanced AI for accurate diagnoses from medical images. The chatbot provides real-time assistance on cataract and glaucoma conditions. Additionally, we integrate Whisper and ESP net for seamless voice-to-text and text-to-voice functionality. All interactions and data are securely stored in an SQLite database for easy access and management.

TruLens provides a robust suite of tools for neural network development and monitoring, including LLMs. You can utilize TruLens-Eval for evaluation and TruLens-Explain for deep learning explainability, independently. Explore these valuable tools while taking on the challenge!

Revolutionize AI with TruLens by TruEra - Your Gateway to Building Better LLM Applications! Build with TruLens, LLMs development and explainability tool by TruEra Leverage AI observability for dynamic app enhancement Collaborate with like-minded individuals! For the Hackathon you can work in a team from 1 to 6 members. In this Hackathon, you can also join with a project from the TruLens 48-Hours Hackathon, provided you adhere to the following rules. Consider it a warm-up, and explore the world of technology by participating in the TruLens 48-Hours Hackathon.

Join the world’s first Custom GPTs Hackathon to create your own AI tools! Innovate with GPTs: Explore the possibilities of creating custom versions of ChatGPT for specific tasks or purposes. No Coding Required: Anyone can build their own GPT; coding skills are not necessary. Hands-on Experience: The primary benefit of this Hackathon is the opportunity to gain practical, hands-on experience with OpenAI's GPT technology. Educational Focus: Use this event as an educational journey to understand the capabilities and applications of GPTs.