Fun with AI: LangChain and GPT-3.5 Turbo Unleashed. Meet Kangala!
Arrays of Light — Practical AI Tutorials for Builders
Implementation-first tutorials on reinforcement learning, LLM engineering, and machine learning. Hands-on code, clear explanations, research-informed.
Practical AI Notes for Builders
Build Better AI Systems, Faster
I am Ravi, and this is where I publish practical walkthroughs on machine learning, LLM engineering, reinforcement learning, and data systems. Every post is designed to be implementation-ready, not just concept-heavy.1
Hands-on Code-first Production-minded Research-informed
Stay updated: get new implementation-first posts in your inbox.
LLM Tutorial Series
Learn by building with LangChain, tools, and applied assistant workflows.
Leveraging Tools in LangChain: Building a Smart Kangala Care Assistant
Reinforcement Learning Series
From tabular control to deep function approximation and policy gradients.
SARSA vs Q-Learning: Understanding On-Policy and Off-Policy RL
Expected SARSA: Bridging On-Policy and Off-Policy TD Control
Deep Q-Networks: From Tables to Neural Function Approximators
REINFORCE: Direct Policy Optimization After Deep Q-Learning
Scaling Stability: Proximal Policy Optimization from Theory to LLM Alignment
Footnotes
The thoughts and opinions shared in this blog are my own. Any product or company names mentioned are trademarks of their respective owners.↩︎