GenAI Field Notes

Building with
AI, day by day.

Not a tutorial. Not a framework. A field manual from someone who actually ships — written session by session, with the people in the room.

By
Vaibhav Lodha
Building klovr.ai
"An LLM is a system that predicts the next token, trained on most of the internet. Every chatbot, every agent, every demo on your timeline — under the hood, this."
Day 01 — the one mental model that changes everything
the series
01
The Only Mental Model

An LLM is a system that predicts the next token, trained on most of the internet.

LIVEMay 26, 2026
02
How It Actually Works

Tokens, embeddings, transformers, self-attention. Math-free version of all the math that runs everything.

NEXTComing soon
03
Prompt Engineering

System prompts, few-shot, chain-of-thought. The craft of talking to LLMs.

UPCOMINGUpcoming
04
RAG in Depth

Chunking, embedding, retrieval, re-ranking. Build a RAG pipeline from scratch.

UPCOMINGUpcoming
05
Agents & Tool Use

From chatbot to agent. Function calling, orchestration, the agentic loop.

UPCOMINGUpcoming
06
Memory Systems

Conversation memory, user memory, world memory. Making AI products that actually know you.

UPCOMINGUpcoming
07
Evaluation & Testing

How do you know it works? Evals, benchmarks, human preference. The boring part that matters most.

UPCOMINGUpcoming
08
Unit Economics & Pricing

The $40K death spiral. Pricing AI products, token budgets, caching strategies.

UPCOMINGUpcoming
09
Production Patterns

Latency, streaming, fallbacks, monitoring. What running AI in production actually looks like.

UPCOMINGUpcoming
10
What's Next

Multimodal, reasoning models, agents at scale. Where all this is going.

UPCOMINGUpcoming
drop notifications

Get each day when it drops.

No newsletter cadence. No sponsored content. Just a link when the next session is ready.

no spam. one email per new session.