Skip to main content

Posts

These posts are not written for experts.
They are written for curious readers — people who enjoy understanding how things work, even if they never plan to build them.
Each post takes a concept from technology or life, removes the jargon, and leaves behind what truly matters: the idea.

I try to write in a way that you can read in one sitting — usually under twenty minutes — and still remember the concept a week later.
No heavy vocabulary, no academic tone. Just stories and analogies that make sense.


What You’ll Find Here
#

ThemeWhat It Means
AI & Everyday LogicSimple explanations of how machines “think” — ai_with_zero_jargon, llm_from_scratch_videos, vector-databases.
Automation in Plain WordsHow computers quietly help us do repetitive tasks — automating_data_sync, genai_app_arch, ragchatbot.
Data & Real-World SystemsWhat happens when numbers meet real problems — from-excel-to-agents-modernizing-sdwis, real-estate-tokenization.
Programming Without PainShort thoughts on how code behaves and why — py_dict_json, marshal_unmarshal, what-not-how.
Money & MindSimple lessons drawn from finance and human patterns — basic_investment_types, million_dollar_algo.

How Often I Write
#

There’s no schedule.
I write when something suddenly makes sense — a concept that feels clear enough to explain in plain language, or when I find a connection between code and life.
Sometimes it happens after long work sessions, sometimes while cooking or driving.

Each post is written to feel like a conversation, not a lecture.


Why “Posts,” Not “Blogs”?
#

Because these are notes worth keeping, not announcements.
They’re ideas that want to be remembered, revisited, and re-understood — one simple paragraph at a time.


These posts are for anyone who believes clarity is better than complexity — and that good ideas are only as strong as the simplicity with which they can be shared.

2025

DevOpsSec Outline for the GenAI Platform
·425 words·2 mins
Quotable Minds: A Personal Collection of Formidable Wisdom
·1366 words·7 mins
Understanding Cryptocurrency
·1256 words·6 mins
Sparknotes: What is Ethereum?
·2256 words·11 mins
LLM From Scratch — Video Lessons Index
·763 words·4 mins
Building an Automated RAG System with AWS Bedrock, Lambda, and Terraform
·1525 words·8 mins
Automating Data Sync with AWS Lambda and S3
·1139 words·6 mins
Dict vs JSON: Understanding Marshal and Unmarshal
·1267 words·6 mins
Understanding Python Dicts and JSON: A Practical Guide with OpenAI API
·1151 words·6 mins
Deploy a Streaming RAG Chatbot with Docker, FastAPI, and a Streamlit UI
·1325 words·7 mins
Migrating GenAI (RAG + Agentic) Development from TypeScript to Python
·1113 words·6 mins
An Introduction to Basic Investment Types
·891 words·5 mins
Standardizing AWS Bedrock with a LiteLLM Gateway
·1341 words·7 mins
Mastering LiteLLM: The Universal Gateway for AI Models
·1072 words·6 mins
10 Types of LLMs Explained Simply
·1210 words·6 mins
Real Estate Tokenization: A Practical Guide
·1078 words·6 mins
From Excel to Agents: Modernizing SDWIS the Right Way
·2021 words·10 mins
RAG Chatbot: Let Your PDF Documents Answer Questions with LangChain
·1001 words·5 mins
Building a Document Processor for RAG Chatbots (Part 3)
·594 words·3 mins
Embedding and Vector Storage with LangChain (Part 2)
·618 words·3 mins
Document Processing and Retrieval with LangChain in Python
·616 words·3 mins
Controlled Feed vs. Push Feed: What Makes Your Rifle Tick?
·752 words·4 mins
Understanding AI Without the Jargon
·524 words·3 mins
MCP Decoded: From Natural Language to Production - Enterprise AI Agents
·2041 words·10 mins
The Million-Dollar Algorithm: How Computers Discover Word Meaning From Scratch
·4331 words·21 mins
Vector Embedding Exercise: King-Queen-Man-Woman
·1850 words·9 mins
Why Python Dominates AI Despite Its Parallel Processing Problem
·1039 words·5 mins
MCP Decoded: From Protocol to Production - Building AI Agents with Natural Language
·2677 words·13 mins
MCP Decoded: From Zero to AI Agent Integration in 10 Minutes
·1703 words·8 mins