
10
4
United States
2+ years of experience
Hi, I'm Hilda! :) I'm currently working as a Data Analytics Instructor and have also led several machine learning and data science projects. I'm exploring internship opportunities to transition into stable industry roles.

Qubic Smart Contract Studio is an AI-powered development environment that democratizes Qubic blockchain development. Our tool eliminates the $200K+ barrier of hiring specialized C++ developers by letting anyone write smart contracts in plain English. Key Features: • AI Code Generation: Natural language → production C++ contracts in seconds • FREE Security Auditing: Real-time vulnerability detection (normally $50K-150K per audit) • One-Click Deployment: Deploy to Qubic testnet/mainnet instantly • 10x Faster Development: What takes weeks now takes minutes • Monaco Editor Integration: Professional IDE experience with syntax highlighting Built specifically for Qubic's unique architecture (15.5M TPS, feeless transactions, C++ QPI contracts), our tool leverages Aigarth AI capabilities and instant finality to provide real-time feedback. ✓ Measurable Impact: $200K savings per project, 10x speed improvement ✓ Real Utility: Expands Qubic ecosystem by making development accessible to everyone ✓ Production-Ready: Full stack implementation with React frontend, FastAPI backend ✓ Post-Hackathon: Launching on Nostromo Launchpad for ecosystem funding Technical Stack: Frontend: React 18, TypeScript, Monaco Editor, Tailwind CSS, Vite Backend: FastAPI (Python), OpenAI API, Qubic SDK Infrastructure: Docker, standalone deployment with mock mode Track 1 - Nostromo Launchpad : We're building the infrastructure that helps OTHER teams move from concept → deployment → community launch. Demo: Functional IDE with AI assistant, security panel, and deployment tools.
7 Dec 2025

Core Engine: IBM watsonx Orchestrate serves as the "Brain," managing the agent's lifecycle, tool connections, and reasoning logic. We utilized the ReAct (Reason + Act) framework, allowing the agent to break down complex user queries into a chain of logical steps (e.g., Step 1: Check Budget. Step 2: Check Policy. Step 3: Formulate Answer.). Knowledge Base: A hybrid ingestion model was used. Unstructured: PDF documents for policies (Leave_Policy.pdf, Hiring_Plan.pdf) enable Retrieval-Augmented Generation (RAG) for answering qualitative questions. Structured: CSV files (employee_data.csv, recruitment_data.csv) provide the quantitative data needed for analytics. Frontend & Deployment: To demonstrate enterprise scalability, we built a custom frontend using Next.js (React). This application acts as a secure interface for the agent. Security: The app uses Next.js API Routes to securely exchange the IBM Cloud API Key for a short-lived IAM Token on the server side. This ensures that sensitive credentials are never exposed to the client browser. Hosting: The entire solution is deployed on Vercel, providing a globally accessible, responsive interface that can be used on any device. Impact & Innovation TalentPilot represents a shift from "Passive HR" to "Active Orchestration." By automating the low-level work of policy checking and data retrieval, it frees up HR professionals to focus on what really matters: people strategy and culture. It ensures 100% compliance with dynamic company rules (like hiring freezes) and provides instant, data-driven answers that would normally take a human analyst hours to compile. This project demonstrates the true potential of Agentic AI: systems that don't just talk, but help us run our businesses better.
23 Nov 2025

ArcFi is a next-generation AI and Arc blockchain-powered finance ecosystem built for a generation that values intelligence, transparency, and automation in every financial move. Instead of relying on one chatbot, ArcFi orchestrates five specialized AI agents, Spending, Portfolio, Perks, Advisors, and Goals, synchronized through a central communication hub that acts as a digital financial boardroom. Together, they analyze and learn from real data in real time to manage every aspect of a user’s financial life. ArcFi merges AI with blockchain through Arc’s EVM-compatible network, using USDC for secure, on-chain, gas-free transactions. The system reads live wallet data to deliver personalized insights and enables conversational finance, where users can speak naturally and act instantly. Each agent has a unique role enhanced with ElevenLabs voice responses: the Spending Agent categorizes and optimizes expenses, the Portfolio Agent tracks assets like crypto, stocks, and real estate, the Perks Agent finds rewards and cashback across 50+ programs, the Advisors Agent connects users with experts through lifelike voice conversations, and the Goals Agent models savings and growth projections with motivational voice feedback. The Chat Orchestrator coordinates all agents, interpreting natural language and generating unified text and ElevenLabs-powered voice outputs. ArcFi lets users say “Send $500 to my landlord,” and it securely executes the USDC transaction via MetaMask while maintaining full control. Privacy stays central, with AI running locally and blockchain ensuring transparency. ArcFi’s agents produce automatic reports, insights, and predictive analytics, creating a living, self-updating ecosystem that anticipates user needs through intelligent text and voice interaction.
8 Nov 2025

Cognitive Cascade showcases the future of collaborative AI through a multi-agent research assistant built on Internet of Agents principles. The system features three specialized agents working in seamless coordination. The Enhanced Search Agent performs live web searches using real APIs, delivering current, relevant information. The AI-Powered Summarizer Agent processes this data with advanced language models to create contextual summaries and extract key insights. The Validator Agent provides AI-driven quality assessment, confidence scoring, and bias detection. Built with production-ready architecture, the system includes real-time monitoring dashboards, persistent session management with SQLite, WebSocket-based live updates, and robust error handling. It demonstrates true agent-to-agent communication aligned with Coral Protocol concepts: structured data passing, specialized agent roles, and an extensible framework for distributed networks. A professional web interface enables immediate testability for judges, while the monitoring system displays real-time metrics, health indicators, and performance analytics. This represents an evolution from prototype to production-ready, highlighting rapid agentic development and real-world application potential. Technical implementation includes a FastAPI backend, fully async processing, multiple deployment options (standalone and Vercel), and graceful fallbacks ensuring reliability. Cognitive Cascade bridges conceptual frameworks with practical solutions, proving how specialized agents can collaborate to achieve capabilities greater than the sum of their parts. Key Features: • Live API-based search integration • AI-powered analysis and summarization • Real-time monitoring and analytics • Persistent session management • Vercel deployment ready • Coral Protocol-aligned architecture • Production-grade error handling
21 Sep 2025