Pratik’s Pakodas 🍿

Continual Learning Without Evals Is Just Drift

the component that cannot be taken for granted

Apr 8 • Pratik Bhavsar

1

February 2026

How to Be a 30x AI Engineer with a Taste

The one skill that separates engineers who thrive in the age of AI from those who become interchangeable.

Feb 19 • Pratik Bhavsar

5

1

Eight Theories of How Agents Strangle SaaS

speculations on suffocation

Feb 9 • Pratik Bhavsar

7

3

January 2026

Pratik's Year in Review: 2025

adventure of a lifetime

Jan 2 • Pratik Bhavsar

6

1

August 2025

My Creativity Manifesto

creation >> consumption

Aug 24, 2025 • Pratik Bhavsar

4

July 2025

Agent Evaluation Playbook

Learn the process behind making reliable agents

Jul 8, 2025 • Pratik Bhavsar

13

April 2025

Maxpool is now on Discord with Agents

World's first AI agent powered community

Apr 16, 2025 • Pratik Bhavsar

2

March 2025

How Deep Wrappers Are Dominating GenAI 🔪

A historical look at winning in GenAI

Mar 25, 2025 • Pratik Bhavsar

4

LLM Chronicles #9: The Power Law of MCP

Understanding the basics of MCP

Mar 11, 2025 • Pratik Bhavsar

7

August 2024

Advice on Vocation from 9 Great Minds

Diverse opinion from psychologists, physicists and others

Aug 11, 2024 • Pratik Bhavsar

3

August 2023

LLM Chronicles #8: How To Select Encoder For Semantic Search & RAG?

A systematic approach to selection of encoders

Aug 22, 2023 • Pratik Bhavsar

5

LLM Chronicles #7: How To Evaluate LLMs? | Open LLM Leaderboard

Let's explore the internals of automated LLM evaluation

Aug 4, 2023 • Pratik Bhavsar

4