How I AI
How I AI

Advanced Claude Code techniques: context loading, mermaid diagrams, stop hooks, and more | John Lindquist

January 26, 2026

AI Summary

5 min read

🎙️ The Voices & The Context

  • The Format: Casual interview with live demos of AI coding tools, blending discussion, screen-sharing, and real-time coding walkthroughs.
  • The Key Players:
    • Guest: John Linquist, Egghead.io instructor and super-user of AI engineering tools like Claude Code and Cursor; known for advanced workshops, newsletters (AI Dev Essentials), and practical AI dev hacks.
    • Host: Claire Vell, product leader and "AI Obsessive" behind How I AI podcast; facilitates with insightful commentary and ties concepts to broader workflows.
  • The Vibe: Educational and energetic—technical deep-dive for senior engineers, buzzing with excitement over efficiency gains, minimal humor but high "aha" moments from demos.

Continue reading the full summary in the app — free to try.

Read Full Summary →

Free • No credit card required

Listen to Audio Summary Open in App

What you'll learn

  • 1 (00:00) **🎙️ Introduction: John Linquist**
  • 2 (04:02) **Context via Mermaid Diagrams**
  • 3 (10:31) **Diagram Generation Workflow**
  • 4 (13:31) **Documentation for AI and Humans**
  • 5 (19:01) **Command Aliases for Efficiency**
  • 6 (21:05) **Building Custom CLI Tools**
  • 7 (26:40) **Claude Code Stop Hooks for Quality**

+ Full timestamped outline available in the app

Show Notes

John Lindquist is the co-founder of egghead.io and an expert in leveraging AI tools for professional software development. In this episode, John shares advanced techniques for using AI coding tools like Claude Code and Cursor that go far beyond basic prompting. He demonstrates how senior engineers can use mermaid diagrams for context loading, create custom hooks for automated code quality checks, and build efficient command-line tools that streamline AI workflows.


What you’ll learn:

  1. How to use mermaid diagrams to preload context into Claude Code for faster, more accurate coding assistance
  2. Creating custom hooks in Claude Code to automatically check for TypeScript errors and commit working code
  3. Building efficient command-line aliases and tools to streamline your AI workflows
  4. Techniques for using AI to generate documentation that works for both humans and machines
  5. How to leverage AI for code investigation and orientation when tackling unfamiliar codebases
  6. Strategies for resetting AI conversations when they go off track

—

Brought to you by:

WorkOS—Make your app enterprise-ready today

Tines—Start building intelligent workflows today

—

In this episode, we cover:

(00:00) Introduction to John Lindquist

(03:15) Using context and diagrams to provide context to AI tools

(05:38) Demo: Mermaid diagrams

(06:48) Preloading context with system prompts in Claude Code

(10:30) The rise of specialized file formats for AI consumption

(13:23) Mermaid diagram use cases

(19:01) Demo: Creating aliases for common AI commands

(21:05) Building custom command-line tools for AI workflows

(26:39) Demo: Setting up stop hooks for automated code quality checks

(35:16) Investing in quality outputs

(36:40) Additional use cases for hooks beyond code quality

(39:19) Quick review

(41:14) Terminal UI vs. IDE

(45:35) Selling AI to skeptical teams

(51:57) Prompting reset tricks

—

Tools referenced:

• Claude Code: https://claude.ai/

• Cursor: https://cursor.sh/

• Gemini: https://gemini.google.com/

—

Other references:

• Zsh: https://www.zsh.org/

• GitHub: https://github.com/

• TypeScript: https://www.typescriptlang.org/

• Bun: https://bun.sh/

• Claude hooks:

How I AI

More from this podcast

 How I AI →