Sharing my final project: Forsa AI, a voice-first interview practice platform. What it does: Candidate picks a role (any role, even a custom title) and optionally uploads a CV → has a real live voice interview with an AI interviewer (GPT-4o via Vapi, WebRTC) → gets an instant scorecard from Claude, cross-referenced against their CV, plus a downloadable PDF action plan with free courses matched to their weakest areas. A few engineering decisions I'm happy with: • Two-model architecture: GPT-4o live for speed, Claude post-call for structured, schema-guaranteed scoring • "Smart Mute" — muting mid-answer tells the agent to wait, not skip the question • A 30-case automated eval suite (npm run eval) that verifies the real prompt/logic wiring, not mocks — catches real regressions like a dead course link before submission, not after 🔗 Repo: github.com/muntherh/forsa-ai-agent 🎥 Demo video: [https://drive.google.com/file/d/1bDp7rxoqwgjNMUu3cMur2ARPlpWFgViy/view?usp=drivesdk] 🌐 Live: [https://forsa-ai-agent.vercel.app] Thanks to everyone here for the feedback along the way — happy to answer questions about the Vapi/Claude wiring if anyone's building something similar

I’m proud to share the Product of my Agentic Predictive Maintenance Copilot for Industrial Assets. 🚀 What started as an engineering problem evolved into a working AI-powered maintenance system: 🔌 Live Industrial Telemetry — connected machine monitoring 🧠 ML-Based Prediction — machine health & failure risk 📡 Anomaly Detection — identify abnormal conditions 🤖 AI Diagnosis — evidence-based fault analysis 💬 Maintenance Copilot — actionable recommendations 🛠️ Work Orders — turning insights into maintenance action The core idea is simple: Predict before failure. Act before downtime. This project brings together Mechanical Engineering + Industrial AI + Automation into one practical solution. ⚙️🤖 Dr Ramanth Polu Sathyaram Sannasi Lori Figueiredo Jay Harish Jethva Ahmed Raoofuddin Sadiya Kauser Ahmad Burt Reynolds 🙏 A special thank you to the judges and mentors who took the time to review, evaluate and provide valuable feedback throughout the project. Especially grateful to Mohammad Arshad, Decoding Data Science, DDS Business Circle and everyone who contributed to this journey.

Hello DDS community! Day 5 of the 8-Day Agentic AI Application Challenge was all about bringing the project to life. Today's milestone highlights: • Polished the UI/UX for a seamless, production-ready user experience. • Successfully executed the default voice agent end-to-end for the first time🎙️ • Completed rigorous end-to-end smoke testing across audio streams and evaluation flows. • Deployed the application live to the Vercel production environment🌐 Thrilled to see the architecture turn into a fully functional live product. How is everyone's deployment coming along?

Hello DDS community Day 4 of the 8-Day Agentic AI Application Challenge was all about fine-tuning and evaluation engineering. Today, I focused on: • Implementing robust evaluation metrics and scoring rubrics. • Upgrading the evaluation engine with advanced structured outputs for reliable performance. • Testing and benchmarking across core scenarios to ensure stability. • Refining error handling and passing clean production builds. Excited for what's coming next in the challenge! How is everyone's progress going? 💡

Hey DDS Community, I’m thrilled to jump into this 8-day sprint alongside all the amazing builders here. 🎯 What I’m Building: Forsa AI (English Edition) An autonomous, conversational AI voice interviewer designed to help students and developers conquer interview anxiety through realistic spoken practice. How it works: 🎙️ Real-time voice interaction — you talk directly with the AI interviewer. 🧠 Adaptive questioning — the agent dynamically tailors technical and behavioral questions based on your live answers. 📊 Instant evaluation — generates a structured performance scorecard with actionable feedback immediately after the call. I’ll be building in public and sharing updates, code milestones, and demos right here on Skool throughout the next 8 days. Looking forward to connecting with fellow participants. What problem are you tackling with your agent? Let's build together! 🛠️