
We created an Agents using MCP enabled tools. we had two tools - one to provide TOP stocks and other to provide buy/sell/hold decision on a particular stock. We used OPEN AI and FINNHUB for market data. We Created investIQ Agent, Created docker image for agent and pushed to dockerHub, Tested Agent operation in the local environment, Configured crossmint wallet with API key provided as part of Beta testing, Emailed all files for publication of Agent to the marketplace, Tested with coral server configured with crossmint wallet. FUTURE PLAN: Make the stock recommendation more robust. Right now, it is a proof of concept. More emphasis was given to be able to use the Coral Framework to deploy the Agent, test it locally and publish to marketplace.
21 Sep 2025

The platform has 4 components: Profile & Goals, Success Steps, Monitoring and Feedback and Live Coaching. Users can create a profile with personal health data. The platform recommends Diet, Exercise, Sleep and Stress management regimen. The unique selling point (USP) is that it provides a dynamic simulation of user's progress if one were to take the steps and adjusts it based on your actions taken. The user gets notification, alerts for their action steps and see their schedule in the calendar. They can talk to Coach, Dietitian, Nutritionist live from the app on the click of a button. Our immediate plan is to roll out a mobile UI with health monitoring devices integration, connect with applications like Apple Health for seamless data integration, monitoring and feedback.
24 Aug 2025

PROBLEM: There is a lack of personalized investment advice application that tracks Stock performance and relevant news, takes into hidden risks (fraudulent transactions/insider trading) for advice and provides complete Portfolio and Scenario Analysis. SOLUTION: We are building a personalized, Agentic AI Finance companion with a mobile interface for easy access to provide portfolio forcecast analysis, investment advice based on risk profile and Complete Portfolio and Scenario Analysis. IMPLEMENTATION We built - Fintra Mobile App: React Native developed using Natively AI co-pilot - deployed to expo.app, expo GO - FintraSync Analysis Engine: Grok, Llama powered multi-agent, MCP, python based analysis engine - deployed to Render - Used Live financial information from finnhub.io - Fraud Detection, Insider Trading: Attempted Agents using Coral Framework. - Voice integration: Attempted on the mobile app using Grok, Llama FUTURE A ROBUST Investment Advisor with - Dynamic Agentic Framework and Platform - Validation framework for analysis results - Include fraud detection, insider trading, human emotion, sentiment analysis and additional economic indicators for better accuracy
8 Jul 2025

βA Healthy Man Has a Thousand Problems, a Sick Man Has only One.β Problem Busy professionals neglect their health β not out of ignorance, but due to crushing schedules, goal-driven lifestyles, and delayed consequences. Most health apps feel like extra work β asking them to track, analyze, or think more, which they simply don't have time or energy for. Small health problems become big ones because early signs are missed, milestones does not get celebrated, and simple protective actions aren't taken in time. Solution A low-friction, proactive Agentic AI health companion that delivers personalized, goal-driven answers to health and fitness queries and protects energy, success, and future β with minimal effort. Recommendation updated to adjust to userβs behavioral pattern and progress.Recommendation updated to adjust to userβs behavioral pattern and progress. Silent Accountability: Private weekly health reports that celebrate wins and flag risks without judgment. Micro-Goals with Auto-Celebration: Track invisible victories ("hydration streak", "sleep improvement") without manual logging. Proactive Health Nudges: Smart, respectful check-ins β only when necessary β to prompt critical interventions. No data sold. No unnecessary cloud syncing. Only user sees the journey unless you choose otherwise. Target Users Busy Professionals (25β55): Tech workers, finance professionals, lawyers, founders, consultants. Executives/Entrepreneurs: People who value results, clarity, and trusted assistants β not clutter or noise. Confidence/Trust in our Recommendation Our Agentic AI delivers truly personalized health actions by deeply understanding each user's data β all while preserving full privacy. Unlike conventional LLMs that generate advice through statistical guesswork, our system leverages custom-built semantic analysis and mental abstracts to reason more accurately, remove hallucinations, and offer guidance users can trust.
1 May 2025

Better Health AI attempts to improve the quality of care by offering different payment models for different health services that ties payment to quality of health outcome while trying to reducing the cost. There have been many care delivery and payment models attempted at state and federal level targeting various diseases, prevention, safety, infection, and other areas of health. The result has been mixed and some are undetermined. There have been many studies and reports published. This project reviews different studies, published articles and reports. It reviews user's scenario of health services and recommends suitable models and implementation strategy with supported facts and figures. The user can work with the application interactively to evaluate different models with success matrix and references for easier decision making. Reducing cost while trying to improve the quality of care may work counter to each other. This project helps to strike the balance and provide examples and approach to achieve this simultaneously.
3 May 2024

Better Health AI is a research initiative in the health care domain that explores and recommends Alternative Payment Model (APM) and Value Based Care (VBC) models. These models ties the payment to quality of health outcome while trying to reduce cost of care. There have been many care delivery and payment models attempted at state and federal level targeting various diseases, prevention, safety, infection, and other areas of health. The result has been mixed and some are undetermined. There have been many studies and reports have been published. This project attempts to scour the internet for different studies, published article and summarize the findings for recommendation. Users of this system can ask questions on various aspects of implementing such a model at state, community, local or federal level for better patient experience.
19 Apr 2024