Writing · Notes
Field notes on shipping AI that works.
Short, opinionated pieces on evaluation, RAG, agents, and the architecture around them — written from what actually broke in production. Most started on LinkedIn; this is the permanent home.
Series
The Honest Guide
A practitioner's tour of the agent-framework stack — what each layer is actually for, what's deprecated, and what you can skip. Start at Part 1.
RAGA Framework, Part 6: Who Evaluates the Evaluator? The Limits of LLM-Based Metrics
Part 6 of a series on evaluating LLM apps with Ragas.
5 minRAGA Framework, Part 5: How to Fix a RAG Pipeline Using Evaluation Results
Part 5 of a series on evaluating LLM apps with Ragas.
5 minRAGA Framework, Part 4: Your Evaluation Is Only as Good as Your Test Data
Part 4 of a series on evaluating LLM apps with Ragas.
6 minRAGA Framework, Part 3: Evaluating a RAG Pipeline with Ragas: A Minimal Working Example
Part 3 of a series on evaluating LLM apps with Ragas.
6 minRAGA Framework, Part 2: Four Metrics That Reveal Why Your RAG System Is Failing
Part 2 of a series on evaluating LLM apps with Ragas.
9 minRAGA Framework, Part 1: Why and how can you evaluate your LLM App?
Part 1 of a series on evaluating LLM apps with Ragas.
5 min- Systems & Cloud
How I Would Design Google Drive at Scale (A System Design Case Study)
Google Drive System Design By Vinay C infographic
6 min - LLM Fundamentals
Tabular Foundation Models Explained: The Missing Piece I Didn't Know Existed
Over the last few days, I spent some time reading about Tabular Foundation Models (TFMs). At first, I assumed they were just another machine learning model. Th…
2 min - Systems & Cloud
IRCTC’s redesign: what may have changed behind the scenes to handle 10x scale
IRCTC’s recent redesign caught my attention, but not because of the new UI.
6 min - LLM Fundamentals
10 LLM application patterns you must know
When people talk about LLMs, the first thing that comes to mind is usually a chatbot.
1 min - Agents & Frameworks
10 AI Agent Design Patterns Every AI Engineer Should Know
Infographic 10 AI Agent Design Patterns Every AI Engineer Should Know
3 min - Systems & Cloud
System Design Interview: Designing Seat Booking for BookMyShow
A common system design interview question is:
6 min - LLM Fundamentals
What Is LLM Distillation? A Beginner’s Guide with Examples
In case you are short on time, check out this infographic for quick summary.
9 min - RAG & Retrieval
FAISS - What AI Engineer needs to know!
If you've been paying attention to the AI space recently — especially with the explosion of LLMs and Retrieval-Augmented Generation (RAG) — you've probably hea…
6 min - Honest Guide · 4
Honest Guide — Google Agent Development Kit (ADK) for Beginners
A practical, code-first introduction to Google's ADK: what it is, the concepts, the building blocks, and a full runnable program at the end.
18 min - RAG & Retrieval
Best PDF Parser for Better LLM and RAG
Your PDF parser is probably the real problem.
3 min - RAG & Retrieval
OKF and RAG: What I Learned While Thinking Through Agentic Knowledge Systems
If you are short on time, go through this infographic, should give you most insights.
9 min - Honest Guide · 3
Honest Guide - LangGraph for Beginners
If you read my LangChain for Beginners post, you built your first create_agent and I told you it runs on something called LangGraph "under the hood." This post…
17 min - Honest Guide · 2
Honest Guide - Langchain for Intermediate
If you read my LangChain for Beginners post, you've already wired up a chat model, built an LCEL chain, done basic RAG, and stood up your first create_agent. Y…
25 min - Honest Guide · 1
Honest Guide - LangChain for Beginners
If you've called an LLM API once or twice and thought "okay, but how do real apps wire this together?" — this post is for you. We'll start from the absolute ba…
20 min - LLM Fundamentals
Understanding Temperature, Top-p, and Top-k in Large Language Models
When you ask a language model to write an answer, it does not simply “know” the next word. Instead, it predicts many possible next tokens and assigns each one…
3 min - RAG & Retrieval
RAG Pipeline Explained: How Retrieval-Augmented Generation Makes AI Answers More Useful
Large language models are impressive, but they have a simple problem: they do not automatically know your private documents, your latest product specs, your in…
6 min - Agents & Frameworks
What is an AI harness, and why does it matter more than your model choice
For a while, I thought picking an AI product came down to one question: which model is underneath? GPT, Claude, Gemini. Smarter model, better product. It seeme…
4 min - Agents & Frameworks
MCP Architecture
Most AI integrations today are custom builds. Your Claude instance needs access to your database? You write a connector. Your IDE needs the same data? You writ…
2 min - RAG & Retrieval
Fast or accurate? Why does good retrieval use two models
Let's say you ship a semantic search feature. Someone types "reset my password" and the top result is a doc about changing email settings. Are they related? Su…
3 min - RAG & Retrieval
Your LLM Has No Memory. Embeddings Are the Fix.
Ask ChatGPT something today, and it only knows what fits inside its context window. So how does it "remember" your past chats, pull the right doc from a knowle…
4 min - RAG & Retrieval
My 6 Learnings About Embedding Models (and Why Many RAG Systems Struggle)
Over the past few days, I’ve been spending time reading about embedding models—not just which ones rank highest, but how they actually behave in real systems l…
3 min - LLM Fundamentals
Large Language Models (LLMs) – Introduction
A comprehensive guide to understanding what LLMs are, how they work, and why they matter.
3 min - RAG & Retrieval
Building Production RAG Systems
Key patterns and pitfalls when building retrieval-augmented generation systems at scale.
2 min - LLM Fundamentals
3 Common LLM Myths which was surprising!
Large Language Models (LLMs) have truly transformed how we interact with technology and information. It's an exciting time, but with all this rapid progress, i…
4 min - Industry Notes
What Satya Nadella Taught Me About AI and Developer Jobs
In today’s fast-paced tech world, it’s easy to get caught in the hype or fear around artificial intelligence. But after lately watching a bunch of videos of ou…
2 min - Systems & Cloud
Demystifying AWS Messaging: SNS vs. SQS
In the ever-expanding world of cloud computing, Amazon Web Services (AWS) provides a suite of services to build scalable and resilient applications. Two key pl…
2 min - Systems & Cloud
Battle for Serverless Supremacy: Google Cloud Run VS Google Cloud Functions
In the rapidly evolving landscape of cloud computing, Google Cloud Platform (GCP) stands out with a diverse array of services tailored to meet the needs of dev…
3 min - Systems & Cloud
Making Movie Magic: How Netflix Uses Amazon Web Services?
Picture this: you're curled up on the couch, about to dive into your favourite show on Netflix.
2 min - Systems & Cloud
Bloom Filters: A Space-Efficient Data Structure
In the world of data management, efficiency is key. Whether it's minimizing memory usage or optimizing search operations, every bit and byte counts. Enter the…
2 min