Our project builds an agentic coordination system that automates lead follow-up and scheduling through an integrated pipeline of modular agents. The system includes two conversational agents (Researcher and SDR) for data enrichment and outreach, plus a central Coordinator agent that ingests inbound replies, uses a watsonx LLM to classify intent, checks calendar availability, and takes action (book meetings, send templated replies, update Airtable records). The Coordinator is resilient and production-ready: it uses Redis for persistent idempotency, the Google Calendar FreeBusy API for real availability checks, and Jinja2-powered reply templates with an LLM fallback for bespoke responses. The backend runs as a FastAPI service containerized for IBM Cloud Code Engine and pulls secrets from secure environment variables; Airtable houses lead state and interaction logs. The design prioritizes accuracy, auditability, and safe operations (signature-verified webhooks, secret rotation). For the hackathon demo we provide end-to-end flows: incoming email → intent classification → booking or follow-up → Airtable update, plus logs/screenshots. This delivers faster, reliable lead conversion and a repeatable foundation for future agentic workflows.
23 Nov 2025
Health Guardian AI is an AI-powered medical understanding and assistance platform designed to help individuals interpret their medical reports in clear, human-friendly language. Many patients receive lab results and diagnostic files full of medical terminology that can be confusing, stressful, or misinterpreted. Our application enables users to upload text or image-based medical reports, automatically extract and analyze content, detect key medical findings, identify associated risk levels, and present results in a simplified and structured format. The platform also generates personalized care plans, covering lifestyle guidelines, diet and nutrition, activity recommendations, and medical follow-up reminders, while clearly stating non-diagnostic safety disclaimers. It further offers an interactive AI health chat assistant trained to provide supportive and educational responses and guide users toward proper medical consultation when needed. Our mission is to empower users with medical awareness, reduce misunderstanding and anxiety, bridge the communication gap between patients and healthcare providers, and assist with informed health discussions, all while maintaining privacy, accuracy, and ethical responsibility.
19 Nov 2025
Problem: Small to Medium Businesses (SMBs) struggle with personalized, scalable outreach due to limited resources. Current solutions are often too complex, lacking the autonomous intelligence needed for dynamic campaign execution. Solution: We built The SMB Sales & Marketing Squad, a cohesive multi-agent system. The workflow starts with the Lead Generation Agent, which uses Apify for targeted data collection and Apollo API for lead enrichment and verification. The Marketing Content Agent applies AI/ML to generate hyper-personalized content. Finally, the Sales Outreach Agent executes the campaign via Gmail and logs all activities to a Google Sheet (acting as the CRM/database). Target Audience: Non-technical SMB owners, solo-preneurs, and small sales/marketing teams. Unique Features/Benefits: The entire system is managed via a unified, user-friendly dashboard built using Lovable AI's free tier. This provides a crucial "human-in-the-loop" oversight for content approval and campaign monitoring. By connecting powerful, accessible tools like Lovable AI, Apollo, Apify, and Google's free services, the project demonstrates an affordable, end-to-end, and highly functional solution perfect for the Internet of Agents theme.
21 Sep 2025
.png&w=256&q=75)
.png&w=640&q=75)
