Shrivu’s Substack

Most Code is Just Cache

As personal apps become trivial, we should stop thinking of code the same way.

Jan 10 • Shrivu Shankar

12

11

1

December 2025

Understanding AI Benchmarks

Tips for interpreting frontier model releases and their SOTA benchmark scores.

Dec 21, 2025 • Shrivu Shankar

16

4

November 2025

How I Use Every Claude Code Feature

A brain dump of all the ways I've been using Claude Code.

Nov 2, 2025 • Shrivu Shankar

275

26

23

August 2025

Betting Against the Models

Speculations on the future of cybersecurity products for AI agents.

Aug 24, 2025 • Shrivu Shankar

13

1

2

AI Can't Read Your Docs

Designing software that today's AI coding agents can actually use.

Aug 17, 2025 • Shrivu Shankar

33

7

2

July 2025

Assistants Aren't the Future of AI

Speculations on what comes after (or instead) of AI assistants.

Jul 19, 2025 • Shrivu Shankar

13

2

Building Multi-Agent Systems (Part 2)

Updated methods for scaling LLM-based agents to handle complex problems reliably.

Jul 5, 2025 • Shrivu Shankar

29

4

June 2025

How to Train Your GPT Wrapper

Improving your agents automatically with experience.

Jun 28, 2025 • Shrivu Shankar

7

1

How I use AI (2025)

Some thoughts on using AI for everyday things.

Jun 8, 2025 • Shrivu Shankar

19

7

2

May 2025

How to Stop Your Human From Hallucinating

When humans sometimes act like confused language models.

May 4, 2025 • Shrivu Shankar

9

2

1

April 2025

Everything Wrong with MCP

Explaining the Model Context Protocol and everything that might go wrong.

Apr 13, 2025 • Shrivu Shankar

118

15

16

March 2025

How Cursor (AI IDE) Works

Turning LLMs into coding experts and how to take advantage of them.

Mar 16, 2025 • Shrivu Shankar

176

26

13