I’m excited to share that I’ve successfully completed Day 3 of the DDS AI Accelerator Bootcamp, marking the final milestone of my HR chatbot build: DDS_HR_MALPOTRA. Over the last three days, I designed and deployed an AI‑powered HR Policy Query Assistant using: - GPT6 Luna / GPT‑4o‑mini - LlamaIndex RAG pipeline - Pinecone vector database - Gradio interface - Hugging Face Spaces deployment What was achieved - End‑to‑end RAG pipeline setup - Pinecone integration for faster and more accurate retrieval - Complete Gradio UI for employee HR queries - Deployment on Hugging Face Spaces - Environment variable configuration and runtime stability - Tested HR queries with structured outputs Demo & Notebooks Hugging Face Space: https://huggingface.co/spaces/Adarshmalpotra/DDS_HR_MALPOTRA https://github.com/Adarshmalpotra/ADARSH-KUMAR-MALPOTRA/blob/main/bootcampsep26/day3-pineconellamaindex-sep27.ipynb My heartfelt thanks Mohammad Arshad Sir for the opportunity and the excellent learning experience.

Today’s DDS Masterclass was a reminder that AI mastery is not about tools — it’s about thinking. The session broke down complex ideas into actionable frameworks: - Structuring agentic systems - Designing robust evaluation pipelines - Building AI products that solve real business problems - Understanding how to scale from prototype to production As someone building MortgageAI for the DDS challenge, this session sharpened my approach and gave me a clearer blueprint for the next phase. Endorsement: If you’re serious about building practical, outcome-driven AI systems, the DDS ecosystem is one of the most disciplined and high-quality learning communities you can be part of. Their masterclasses consistently deliver clarity, structure, and real-world applicability — highly recommended for builders, analysts, and product leaders. #DecodingDataScience #DDSMasterclass #AIChallenge #AgenticAI #ArtificialIntelligence #MachineLearning #DataScienceCommunity #AIEngineering #BuildInPublic #TechInnovation #LearningInPublic #AIProductDevelopment #FintechAI #MortgageAI #DigitalTransformation

Excited to kick off the AI Accelerator Weekend Bootcamp – 7th Edition by Decoding Data Science. Looking forward to three days of hands‑on learning, practical AI skills, and building real applications using LLMs and modern AI tools. This is the beginning of a focused journey to deepen my capabilities in AI engineering, agentic workflows, and enterprise‑grade automation. Eager to learn, build, and grow with this amazing community. Thank you Decoding Data Science for creating such a powerful platform for practitioners and professionals. Let’s build something meaningful. #AI #AgenticAI #DecodingDataScience #Bootcamp #AIEngineering #BuildInPublic

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.

Thrilled to share my final submission for the DDS AI Challenge 2026 — MortgageAI, a fully automated, no‑code/low‑code mortgage underwriting engine built end‑to‑end using n8n, Anthropic Claude Sonnet, OpenAI GPT5/GPT4o, and Google Cloud. MortgageAI delivers FOIR, EMI, loan eligibility, multi‑bank underwriting, document checklists, and email-ready summaries — What I Built Deterministic FOIR/EMI engine Multi‑bank underwriting logic (HDFC, ICICI, SBI; Axis/Kotak next) AI‑powered PDF parsing with fallback models Automated Drive folder creation Google Sheets logging Email delivery with underwriting summary Fully orchestrated through n8n Multi‑Model Strategy Claude Sonnet 4.5 → Underwriting logic GPT5 / GPT4o → PDF parsing fallback Deterministic JSON schema → Zero hallucinations Performance Underwriting latency: 1.8–2.4 sec Workflow latency: 3.5–5 sec End‑to‑end: ~6–7 sec Cost/run: $0.002–$0.006 Live Demo & Links n8n Workflow Demo: https://lnkd.in/gHwbpTBs Project Website: https://lnkd.in/dVXxMrUb Repo: https://lnkd.in/dfKxfgaP This challenge pushed me to design a production‑grade underwriting engine using a no‑code/low‑code stack — and I’m proud of the final outcome. Grateful to Decoding Data Science, the mentors, and the entire community for the energy throughout the challenge. hashtag#DDSAIChallenge2026 hashtag#AIChallenge hashtag#MortgageAI hashtag#FintechInnovation hashtag