Debabrata Pruseth

Debabrata Pruseth is an AI Architect and Applied AI Researcher specializing in large language models, prompt engineering, and applied AI systems. His work connects research with real-world implementation. He enjoys blogging and traveling.

How I built a beginner-friendly skin-cancer detector

How I built a beginner-friendly skin-cancer detector Read More »

Visualising Change from Space — A Beginner’s Guide to ML with Satellite Data – Part 1

Explore how machine learning and satellite imagery can reveal how cities grow, how nightlights change, and how vegetation evolves. Three notebooks (India nightlights, Delhi urban map, Singapore NDVI) walk beginners step-by-step from visualization to a supervised ML example.

Visualising Change from Space — A Beginner’s Guide to ML with Satellite Data – Part 1 Read More »

Agentic AI – LLM with SQL – Beginner Bootcamp

AI Agent_LLM with SQL

In this post, you’ll learn how to build your own AI SQL Agent — a tool that transforms natural language into SQL queries and executes them on a real database.

In real-world teams, everyone — from marketers to HR to analysts — wants to “talk to the database” without needing to know SQL. But data lives behind structured queries. That’s where LLMs like GPT-4 shine: they understand natural language and, with the right schema and safety controls, can generate SQL queries that pull live data.

No prior coding experience required. Just download the code, run it, enhance it — and start learning!

Agentic AI – LLM with SQL – Beginner Bootcamp Read More »

Agentic AI – LLM with RAG – Beginner Bootcamp

AI Agent_LLM with RAG

In this post, you’ll learn how to build your own document-reading AI assistant — an intelligent tool that can read and understand documents like PDFs, Word files, Excel sheets, HTML pages, JSON files, and more using OpenAI’s powerful language models combined with a cutting-edge technique called RAG (Retrieval-Augmented Generation).

No prior coding experience required. Just download the code, run it, enhance it, and start learning!

Agentic AI – LLM with RAG – Beginner Bootcamp Read More »

Agentic AI – LLM with Web Scraping – Beginner Bootcamp

In this beginner-friendly bootcamp, learn how to create a smart web agent that scrapes websites, processes content with GPT-4, and answers user questions intelligently. You’ll start with basic LLM-based querying and then upgrade to a scalable Retrieval-Augmented Generation (RAG) system using vector databases like FAISS. Perfect for Python and AI learners!

Agentic AI – LLM with Web Scraping – Beginner Bootcamp Read More »

Agentic AI – LLM with API Calls – Beginner Bootcamp

🧠 Build Your First Agentic AI!
Curious how ChatGPT can actually call functions and fetch live data?

In our latest Beginner Bootcamp, learn how to create a smart Weather Agent using OpenAI’s GPT-4 and WeatherAPI — no advanced coding required!

Agentic AI – LLM with API Calls – Beginner Bootcamp Read More »

Agentic AI for Beginners – Learn by Building Your First App

🚀 Build Your First Agentic AI App (With Code Example!)

In this beginner-friendly bootcamp, you’ll learn how to build a multi-agent AI application from scratch. We’ll walk you through the core architecture of agentic systems and show you how to bring it to life with a real-world project — an AI-powered Workshop Planner and Meeting Assistant.

You’ll get:

✅ Step-by-step tutorial

💡 Ready-to-run Python code

🔧 Hands-on experience with LangChain and LangGraph

Just download the notebook, run it in your Python environment (like Google Colab), and start building. Tweak it, expand it, and you’re on your way to creating your own AI agents!

Agentic AI for Beginners – Learn by Building Your First App Read More »

End-to-End Data Quality Management Framework (DQMF) in Banking with GenAI Integration

DQMF and GenAI

Data quality is mission-critical in banking, as poor data can erode trust and even impact revenue (businesses reported an average 31% revenue loss due to bad data in 2023). Banks handle diverse data (customer info, transactions, risk metrics, etc.), and regulators demand ( BCBS239, GDPR etc) that this data be accurate, complete, timely, and well-governed.
Generative AI (GenAI) offers new ways to automate and enhance data quality management across these phases. Modern AI can summarize and generate documents, extract and classify information, and even assist in detecting data issues, thereby accelerating data governance and compliance tasks. Below, we break down the key DQMF phases – from data creation, storage, processing, usage, to archival and deletion – highlighting critical activities and how GenAI can realistically improve or streamline outcomes in each. We then present a structured table summarizing GenAI applications for each phase, implementation steps, and example prompt templates.

End-to-End Data Quality Management Framework (DQMF) in Banking with GenAI Integration Read More »

Beyond the Laughs: Understanding Bias in AI-Generated Humor

Take a revealing journey into the burgeoning field of artificial intelligence and its foray into humor. This crucial exploration uncovers the often-surprising ways hidden biases surface through AI’s attempts at laughter. Learn why proactively guiding AI creativity is paramount to generating truly uplifting and inclusive content for all. We provide practical and powerful techniques to steer AI humor generation towards positive storytelling, effectively navigating its whimsical yet inherently imperfect understanding of what’s truly funny.

Beyond the Laughs: Understanding Bias in AI-Generated Humor Read More »

Alan Turing: Love, Math, and the Dream of Thinking Machines

Alan Turing’s audacious journey fused heartache, genius, and an unbreakable love for mathematical beauty. Discover how his revolutionary vision of thinking machines defied societal norms, shattered prejudices, and ignited the unstoppable evolution of artificial intelligence. Turing’s legacy proves that true brilliance transcends cruelty, rewriting the future with courage and clarity.

Alan Turing: Love, Math, and the Dream of Thinking Machines Read More »

Scroll to Top