This week has been all about building and learning. I officially joined the Agentic AI Demo Challenge and started working on Forsa, an AI-powered recruitment platform. Along the way, I learned that building a real AI product is much more than prompting—it’s about solving real problems, designing good user experiences, and continuously improving through feedback. Over the next month, my focus is to: - Complete and refine Forsa. - Strengthen my AI application development skills. - Share my progress publicly and learn from the DDS community. Grateful to be part of this amazing community. Looking forward to what’s next.

My Journey with Decoding Data Science: From a Team Builder to an AI Creator When I joined Decoding Data Science, I didn't know that it would become one of the biggest turning points in my tech journey. It all started with a team challenge. A group of us came together to build PromptCoach, an application designed to help people write better AI prompts. It was my first experience working with a team to solve a real problem using AI. We presented our project at the in5 Innovation Centre in Dubai, and although I was nervous standing in front of everyone, it gave me confidence that I could actually build and present technology that helps people. That experience changed something in me. When the AI Application Challenge was announced, I decided to challenge myself by building an application on my own. I created AgriSense AI, an AI-powered smart agriculture solution. Unlike the team project, this time every decision, every challenge, and every solution depended on me. There were moments when I wanted to give up. Debugging wasn't easy, learning new tools wasn't easy, and there were times I questioned whether I could finish. But every day of the challenge taught me something new. One moment I will never forget was the final day. One of my favourite memories was the final day of the AI Application Challenge. As the countdown clock ticked closer to zero, I had the privilege of hosting the countdown and cheering on fellow participants as they submitted their projects. It was inspiring to witness everyone's hard work, determination, and excitement. In that moment, I realised that Decoding Data Science is more than a learning platform—it's a community that celebrates every builder's success. That wasn't the end of the journey. Soon afterwards, I received another unexpected blessing. I was selected to become a Decoding Data Science Ambassador, giving me the opportunity to inspire and support others who are beginning their own AI journeys. Then came another surprise. I was announced as the winner of the Python Essentials Certificate worth $400. It wasn't just about receiving a certificate. It was a reminder that showing up consistently, engaging with the community, and putting in the effort never goes unnoticed.

Introducing Lumen AI — an AI-powered Dubai Utility Bill & Energy Assistant, built during the DDS Enterprise AI Bootcamp by Decoding Data Science. The problem it solves: Understanding a DEWA bill isn't easy. Electricity slabs, water charges, fuel surcharge, housing fee, sewerage fee, and VAT can make it confusing—especially for new residents. Lumen AI explains bills in plain language and provides accurate estimates using official DEWA tariff information. You can ask it: 🔹 "Why did my DEWA bill increase this month?" 🔹 "Estimate my bill for 3,500 kWh." 🔹 "How do electricity slab rates work?" 🔹 "How can I reduce my monthly energy bill?" Tech Stack ⚙️ LlamaIndex (RAG)📦 Pinecone🤖 OpenAI GPT-4o-mini 🌐 @Flask 🐳 Docker, Inc 🤗 Hugging Face Spaces What I learned ✅ Better data beats bigger models. ✅ RAG quality depends on the knowledge base. ✅ Building and deploying a real AI product is the best way to learn. 🚀 Live Demo: https://huggingface.co/spaces/nipunkavindaAI/LumenAI 💻 GitHub: https://github.com/NipunKavinda95/LumenAI Thanks to Mohammad Arshad and Decoding Data Science for another hands-on learning experience. DDS Business Circle Dubai Electricity & Water Authority - DEWA #AI #GenerativeAI #RAG #LlamaIndex #OpenAI #Pinecone #HuggingFace #DEWA #Dubai #BuildWithAI #DecodingDataScience #LearningInPublic

Over the past two days, I’ve been diving deep into AI product development and Retrieval-Augmented Generation (RAG)—gaining both strategic frameworks and hands-on experience building real-world AI solutions. 🚀 Workshop 1: AI Product Thinking & RAG Foundations The opening session focused on the bridge between business requirements and technical execution—understanding how successful AI products are actually designed and built. Key Learnings: Idea Translation: Converting raw concepts into clearly defined AI project scopes. Problem-First Mindset: Identifying core business challenges before picking the tech stack. Data Strategy: Defining data requirements and effective ingestion strategies. LLM Evaluation: Comparing model capabilities, latency, and cost structures across different providers to select the best fit. Parameter Tuning: Mastering OpenAI configuration parameters like Temperature, Top-P, and Max Tokens. RAG Architecture: Understanding the end-to-end workflow 🤖 Workshop 2: Building a RAG Chatbot with LlamaIndex The second workshop was all about hands-on implementation in Google Colab, building a functional RAG pipeline from scratch. Tech Stack: ⚙️ LlamaIndex: Document ingestion, chunking, indexing, retrieval orchestration, and context management. ⚙️ Gradio: Rapid deployment of a clean, interactive chatbot user interface. Key Takeaway: LlamaIndex simplifies complex RAG engineering tasks that would otherwise require extensive custom boilerplate. It allows developers to focus on solving core business problems rather than managing underlying infrastructure. 💡 Practical Project: DDS HR Chatbot To apply these concepts directly, I built an HR Chatbot for DDS using the RAG architecture. Key Features & Impact: Retrieves answers directly from internal HR documents. Delivers accurate, context-aware responses. Minimizes hallucinations by grounding answers strictly in company knowledge. Demonstrates how domain-specific AI can transform internal knowledge access and employee support.

Some people collect stamps... I seem to collect DDS Bootcamps. 😄 Excited to be joining the July 2026 Decoding Data Science (DDS) Bootcamp! There is always something new to learn in AI, and every session brings fresh perspectives, practical insights, and a chance to connect with an amazing community. Looking forward to another weekend of learning, growing, and keeping up with the ever-evolving world of AI. 🚀