Efstathios Zaxarias Zahri@deezm36582102

NataCONNECT is a personal finance application built to run locally on hardware the user owns, bringing together four areas people usually manage through separate apps or spreadsheets. Shield protects payment cards through user defined rules across five categories, spending limits, time restrictions, seller verification, category blocks, and custom rules, and shows the reason behind every blocked or flagged transaction. It also includes Emergency Lock, which locks a device out of the wallet with a six digit passcode if lost or stolen, showing when the lock happened and which card is linked, and NataScan, which checks whether a website is trustworthy, based on domain age, HTTPS usage, and community reports. Practice is a trading simulator built around virtual accounts, each starting with a set amount of simulated money in euros or dollars, that users can trade across real market assets, backed by live market data showing current, highest, and lowest prices along with percentage change. Every closed trade updates a skill level from zero to one hundred, moving the user between beginner, intermediate, and advanced, along with a virtual balance, total trades, win rate, and achievements for larger profits. Guide is a financial assistant that answers questions about saving and investing in plain language, making clear it offers general information rather than advice and never carries out a transaction. It runs on models served through the Fireworks AI API on AMD hardware, and its answers connect back to Practice, letting a user test an idea with simulated money right after asking. Goals turns savings targets and spending limits into clear, adjustable numbers across categories such as rent, vacation, and emergency funds, with optional deadlines and a personal or shared family scope. Goals can also be marked Shield protected, so money set aside is covered by the same rules already running in Shield, with the app showing how much protected money is safeguarded.

What Conata Is Conata is a full-featured business management platform for small and medium businesses. It helps owners and employees manage finances, workers, schedules, and communication – all in one place. Two user roles: Admin (owner) – full control | Worker (employee) – personal portal Core Business Features Admin: Dashboard with metrics + charts | Finances with transactions + CSV upload | Worker management with productivity/satisfaction scores | Schedule calendar | Inbox for worker submissions | Announcements (broadcast or direct) | Fraud alerts + cases | AI Assistant chat | Audit log Worker: Dashboard with salary, hours, schedule | My schedule (4 weeks) | My earnings (hours log + chart) | Submit feedback (complaint/suggestion) | Messages from admin | AI Assistant (personal data only) AI Multi-Agent Features Three Advisor Agents – When admin asks a question, Manager Agent dispatches to three personas: Olivia (Optimist) – Sees growth, opportunities → "Revenue is up 12%!" Peter (Pessimist) – Spots risks, inefficiencies → "Expenses grew 8% faster than revenue." Rita (Realist) – Data-driven, balanced → "Profit margin stable at 22%." FraudSquad (4 agents) – Sequential handoffs for suspicious transactions: Triage Agent – Extracts amount, sender, receiver Entity Checker (Finnhub + Claude) – Company financials, news, offshore status Risk Assessor (Claude) – Fraud risk score (0–100) + reasoning Escalation Agent – Auto-approve, manual review, or file SAR With pre-loaded data(for the hackathon) ready to test immediately, we prove that multi-agent collaboration isn't just a demo – it's a practical tool that helps small businesses make better decisions and catch fraud faster. Conata – One Platform. Zero Blind Spots. * for the judges, we have putted already some business data so you can see how the app works on real scenarios*

To participate in the hackathon, simply click Sign up with AMD. If you are not already a member of the AMD AI Developer Program (ADP), you will need to create an account. ADP members can access AI tutorials, experts, and community support. In addition, new members can claim a free month of DeepLearning.ai pro, $100 in AMD GPU cloud credits, and $50 in Fireworks AI API credits. All hackathon participants will receive on hackathon launch additional compute and API credits for their projects. Ready to build what's next on AMD? Sign up with AMD below to secure your spot.

📅 June 12–19, 2026 • June 12: Kick-off Stream • June 12–19: Online Build Phase • June 19: Project Submissions Ends 🌍 Fully online hackathon. Join and build from anywhere in the world. 🤝 Build practical enterprise workflows where AI agents communicate, coordinate, exchange context, and complete work together. 🧠 Powered by Band and Codeband, built for collaborative AI systems and agent orchestration. 🏆 Prize Pool: $10,000+ 🧑‍💻 Apply now to build the next generation of enterprise multi-agent systems.