Series
LLM Engineering
01Types of LLM Quantization: By Timing, Scope, and Mapping
PTQ, QAT, INT8, INT4, and NF4 explained through timing, scope, and mapping choices.
•15 min read- 02
Skills vs LangChain, LangGraph, MCP, and Tools: A Practical Architecture Guide
LangChain/LangGraph run workflows, MCP exposes capabilities, tools do actions, and skills package outcomes.
•13 min read - 03
Practical LLM Quantization in Colab: A Hugging Face Walkthrough
A Colab-first Hugging Face guide to quantize open LLMs and run real inference code.
•14 min read - 06
GPTQ vs AWQ vs NF4: Choosing the Right LLM Quantization Pipeline
A practical comparison of GPTQ, AWQ, and NF4 quantization pipelines for LLM inference.
•14 min read - 07
SFT for LLMs: A Practical Guide to Supervised Fine-Tuning
Supervised fine-tuning teaches LLMs task behavior before preference tuning and RLHF.
•11 min read - 08
RLHF in Practice: From Human Preferences to Better LLM Policies
RLHF turns human preference signals into policy updates for more useful LLM behavior.
•11 min read - 09
PEFT, LoRA, and QLoRA: A Practical Guide to Efficient LLM Fine-Tuning
PEFT, LoRA, and QLoRA cut fine-tuning cost while keeping strong task performance.
•13 min read 
10LLM Model Naming Conventions: How to Read Names and Why They Matter
Learn how to decode LLM names like 8B, Instruct, Q4, and context-window tags.
•11 min read- 11
Why Embeddings Matter: Solving Key Issues in Data Representation
How do computers understand that 'King' - 'Man' + 'Woman' = 'Queen'? Embeddings convert words int...
•14 min read - 12
What are Logits in Machine Learning and Why They Matter
Logits are the raw, unnormalized scores output by a neural network before they are turned into pr...
•11 min read - 13
Text Decoding Strategies: Greedy, Beam Search, and Sampling
How does an LLM choose the next word? It's not just random. We explore Greedy Search, Beam Search...
•15 min read - 14
RLHF Explained: How We Teach AI to Be Nice
ChatGPT isn't just smart; it's polite. How? Reinforcement Learning from Human Feedback (RLHF). We...
•13 min read - 15
Mastering Prompt Templates: System, User, and Assistant Roles with LangChain
Prompt templates turn messy string concatenation into structured, testable message flows for reliable LLM applications.
•13 min read - 16
Prompt Engineering Guide: From Zero-Shot to Chain-of-Thought
Is Prompt Engineering a real skill? Yes. We explore the science behind talking to AI. Learn how Z...
•12 min read 
17Multistep AI Agents: The Power of Planning
Simple AI agents react one step at a time. Multistep agents are different: they create a full pla...
•15 min read
18LoRA Explained: How to Fine-Tune LLMs on a Budget
Want to train your own LLM but don't have 100 GPUs? LoRA (Low-Rank Adaptation) lets you fine-tune...
•13 min read- 19
How to Develop Apps Using LangChain and LLMs
LangChain is the glue that connects LLMs to your data. We explain Chains, Prompts, and Agents, and how to build your first app.
•15 min read - 20
Guide to Using RAG with LangChain and ChromaDB/FAISS
Build a 'Chat with PDF' app in 10 minutes. We walk through the code for loading documents, creati...
•14 min read
04LLM Skills vs Tools: The Missing Layer in Agent Design
Tools do one action; skills orchestrate many steps. Learn why this distinction makes agents far more reliable.
•15 min read- 05
LLM Skill Registries, Routing Policies, and Evaluation for Production Agents
After tools and skills, this is the control plane: registry design, routing rules, and evaluation loops.
•14 min read