From 5–13 September, I’ll be building, learning, and pushing myself to turn an AI idea into something real. A challenging week ahead — and I can’t wait to share what I’m working on soon. 👀✨ Thank you to Mohammad Arshad Decoding Data Science for organising this opportunity, supported by Ai Everything Abu Dhabi, DDS Business Circle, and JetBrains. #AgenticAI #AIChallenge #ArtificialIntelligence #BuildInPublic #DataScience #Innovation #LearningJourney

✨ Wrapping up the final checkpoint of the Decoding Data Science **AI Accelerator Bootcamp** by shipping my project: *Chappie — DDS HR Intelligence* 🤖💼 Instead of building a simple toy wrapper, the goal across Workshops 2 and 3 was to design a production-style Retrieval-Augmented Generation (RAG) system that HR teams and employees can actually trust. Here is a breakdown of the architecture, engineering decisions, and key takeaways from the build: 🛠️ Architecture & Tech Stack : ❇️ Orchestration & Data Pipeline: Built with LlamaIndex to chunk, index, and retrieve unstructured enterprise HR documents (handbooks, leave policies, and remote work FAQs). ❇️ Vector Database: High-performance indexing and semantic search powered by Pinecone. ❇️ Reasoning & Generation: Grounded LLM generation with OpenAI embeddings for high-dimensional semantic matching. ❇️ Interactive UI: A custom, dark-themed Gradio interface deployed directly to Hugging Face Spaces, equipped with session memory and quick-access prompt presets. 💡 Core Engineering Focus Areas 🔹 Strict Document Grounding & Citations: Every response provides verifiable citations directly referencing the source policy (e.g., Source: DDS Leave Policy (Synthetic) v1), eliminating ungrounded speculation. 🔹 Boundary & Fallback Handling: When a user asks for personal/confidential records outside the document scope (such as real-time individual leave balances), the assistant avoids hallucination and routes them to official support channels. 🔹 Session State & UX: Built-in session memory to retain conversational context, paired with quick-access buttons for standard HR questions (parental leave, carry-over rules, health insurance). 🔗 Live Hugging Face Space: https://lnkd.in/dz6MatpR Returning to build with @Decoding Data Science once again reinforced that enterprise AI isn't just about prompt tuning—it's about clean data pipelines, evaluation benchmarks, and reliable guardrails. On to the next build! 💻

It was my first time participating in the bootcamp with Decoding Data Science (DDS) and it was a great experience overall. Mr. Mohammad and the team have worked hard to create a detailed and comprehensive bootcamp that enables participants from various backgrounds to understand the material and apply it towards the project. The DDS team and the participants of the bootcamp were all supportive which made the process of learning and applying AI skills easier.

Ready to move beyond watching tutorials and start building with AI? Join the AI Accelerator Bootcamp: AI Curious to AI Builders Sep and take your first step toward creating practical AI solutions. This hands-on learning experience will help you: → Understand the foundations of modern AI → Explore powerful AI tools and workflows → Build practical AI-powered projects → Gain real-world, hands-on experience → Turn your AI knowledge into something you can actually create Don’t just learn AI. Build with it. Join Here https://nas.com/artificialintelligence/challenges/ai-accelerator-bootcamp-ai-curious-to-ai-builders-sep/home early bird offer Your journey from AI Curious to AI Builder starts here.

Happening this Tuesday, September 1 at 7:00 PM GST Learn how to orchestrate AI coding agents for building new projects and working with existing codebases. This practical session will introduce AgentGrid, an infinite canvas for managing AI coding agents. Key takeaways: • Build cross-harness agent teams • Add AI workflows to an existing codebase • Coordinate agents across coding projects • Maximize your AI subscriptions without running out of tokens The session will be led by Michael Yagudaev, co-founder of AgentGrid and a software engineer and founder with 16 years of experience building AI and technology products. You can also participate in the live Kahoot and win up to $1,000. Register here: https://nas.com/artificialintelligence/events/ai-explorer-ai-demos-ai-use-cases-and-q-a-1779272460828 Live participation is required.