I had the privilege of attending a recent session with DDS AI and learned so much about thinking about your product when working with AI, Agentic AI vs RAG, Prompt Engineering, and using the appropriate language model for your use case. One major insight was that when building with AI you want to start with a real problem you are trying to solve instead of picking the latest and greatest model or trying to make another chatbot. We discussed how Agentic AI is capable of reasoning, using tools, having a memory, and acting on a plan. While RAG allows your AI to connect with verified documents to create more grounded answers. I’m also learning the hard way how important it is to just try things out, be your own user when testing, write down what works, and iterate. Just because one model performed better for one task doesn’t mean they will for another task. Select your model based on what the user needs and what your project requires. I’m an Electrical Engineering student, and these are lessons I will take with me as I start to brainstorm for my senior design project. I’ve been working on an idea for a while now. It’s an AI called CampusMate, an intelligent university assistant to help students keep track of classes, search academic documents, and plan their semester. Thanks to Decoding Data Science and the DDS Business Circle, the mentors that lead the sessions, and the AI community as a whole. I can’t wait to learn more, try new things, build, reflect on my successes and failures, and share my journey. #DDSNextGen #DDSAmbassador #DecodingDataScience #DDSBusinessCircle #AgenticAI #ArtificialIntelligence

Today I focused on improving Nexa AI and making the agent workflow smarter. What I worked on today: ✅ Connected the CV Agent ✅ Added the Learning Agent for personalized roadmaps ✅ Improved career recommendations using skill-based matching ✅ Added dynamic match scores based on user profiles ✅ Tested and fixed issues across the agent system Today’s lesson: building AI applications is not only about adding features — it’s about making different parts of the system work together smoothly. More improvements coming soon! 🚀

I’m thrilled to kickstart my journey in the DDS Agentic AI Challenge officially hosted by Decoding Data Science (popularly known as DDS) and the good folks over at DDS Business Circle. Artificial Intelligence fascinates me. I love learning about automation and building cool things that can solve problems. What better way to learn than jump into a community of inspired builders and just start building? Project Goals: My Project: CampusMate AI – Smart University Student Assistant I’ll be building CampusMate AI, an Agentic AI application that helps university students get things done quicker and easier. Problem CampusMate AI Wants to Solve that students waste too much time navigating between their university portal, learning management system, email client, timetable, academic calendar, online course documents, and more to find answers to questions or access important resources. My Solution: CampusMate AI will be more than just your standard university chatbot. Imagine having a personal assistant that can reason about your requests, remember previous conversations, and help you complete tasks that students need done every day. Here are some of the features I plan to build: ✅ AI-powered study planner ✅ Assignment and deadline tracking ✅ Intelligent search of university documents with RAG (Retrieval Augmented Generation) ✅ Study recommendations ✅ Remember conversations to provide a more personalised experience ✅ Plan and prioritise tasks ✅ Integrates with your calendar (TODO:) ✅ Track your academic progress I will be using: ChatGPT (For planning the user experience, architecting, designing, and overall application guidance/prototyping) Python LangChain once I learn about it then I can integrate it in my website. LangGraph once I learn about it then I can integrate it in my website. LlamaIndex once I learn about it then I can integrate it in my website. SQLite once I learn about it then I can integrate it in my website. I’ll be documenting my learning progress with these tools throughout the challenge.

A few weeks ago I joined the Decoding Data Science’s 8-Day Building AI Application Challenge. I placed in the top 25 from 295 participants worldwide, what I walked away with is worth more than a podium finish. 8 days, one idea, a fully deployed AI application built from scratch. I built Cookable, an AI powered recipe assistant that takes whatever ingredients you have and generates 5 detailed cookbook quality recipes in seconds. Built with Streamlit, Groq API, and LLaMA 3.3 70B. Here is what I actually learned: • Prompt engineering is harder than it looks. Small wording changes had a bigger impact on output quality than anything else. • Error handling is not optional. 20 test cases on Day 4 found three failure modes I had not anticipated. Each one taught me something. • The gap between working and polished is almost entirely CSS and session state. Core logic was done by Day 3. The rest was making it something I was proud to share a link to. • Deploying something real changes your standards. The moment the app went live, edge cases stopped being optional. I did not get a leaderboard position but I took home something better: a deployed app, a sharper skillset, and a clearer understanding of what it actually takes to build something real from scratch. That feels like enough. Grateful to Decoding Data Science and Mohammad Arshad for building a challenge that forces you to ship, not just study. Live app: https://cookable-bydurgaanand.streamlit.app/ GitHub: github.com/Durga-Anand-2006/cookable Decoding Data Science DDS Business Circle #DecodingDataScience #BuildingAIApplicationChallenge #AIChallenge #BuildInPublic

Feeling incredibly grateful today! 🙏🎉 I was selected as a Top 25 Finalist from 295 participants worldwide in the Decoding Data Science Build AI Application Challenge (12th Edition)! My project, AgriSense AI, focuses on helping farmers make smarter irrigation decisions by using AI to monitor soil moisture and humidity without the need for constant physical inspection. This challenge pushed me to learn, experiment, and build something meaningful. More than the recognition, I'm thankful for the knowledge, mentorship, and amazing community that made this journey so rewarding. A huge thank you to Mohammad Arshad and everyone at Decoding Data Science for creating opportunities that inspire students like me to keep growing. This is only the beginning. On to the next challenge! 🚀💙 #DecodingDataScience #BuildInPublic #AI #Learning #AgriSenseAI #StudentJourney #KeepBuilding #NeverStopLearning