Advanced Claude Code techniques: context loading, mermaid diagrams, stop hooks, and more | John Lindquist
How I AI26 Tammi

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

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: https://code.claude.com/docs/en/hooks

Where to find John Lindquist:

Website: https://egghead.io

Newsletter: https://egghead.io/newsletters/ai-dev-essentials

LinkedIn: linkedin.com/in/john-lindquist-84230766

X: https://x.com/johnlindquist

Where to find Claire Vo:

ChatPRD: https://www.chatprd.ai/

Website: https://clairevo.com/

LinkedIn: https://www.linkedin.com/in/clairevo/

X: https://x.com/clairevo

Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email jordan@penname.co.

Tämä jakso on lisätty Podme-palveluun avoimen RSS-syötteen kautta eikä se ole Podmen omaa tuotantoa. Siksi jakso saattaa sisältää mainontaa.

Jaksot(93)

This solo builder runs 24/7 local AI on his own hardware | Alex Finn

This solo builder runs 24/7 local AI on his own hardware | Alex Finn

Alex Finn is an AI builder, YouTuber, and the creator of Vibe Code Academy, a community for people learning to build with AI tools. He runs one of the most ambitious local AI setups I’ve come across: ...

13 Heinä 35min

GPT-5.6 Sol vs. Claude Fable: Why OpenAI’s new model crushes my benchmark

GPT-5.6 Sol vs. Claude Fable: Why OpenAI’s new model crushes my benchmark

GPT-5.6 Sol is back, and I ran it through my full How I AI vibe benchmark against GPT-5.6 Terra, Luna, Claude Fable 5, and Sonnet 5 across five categories: PRDs, prototypes, wireframes, debugging, and...

9 Heinä 36min

What a harness is and how to build one with Claude Agent SDK

What a harness is and how to build one with Claude Agent SDK

Everybody is saying, “It’s not the model, it’s the harness,” but almost nobody stops to explain what a harness actually is. So I did. I built one live on the show: a Sentry bug-debugging harness for m...

8 Heinä 24min

How I run autonomous coding agents from my phone with OpenAI Symphony + Linear | Alessio Fanelli (Kernel Labs)

How I run autonomous coding agents from my phone with OpenAI Symphony + Linear | Alessio Fanelli (Kernel Labs)

Alessio Fanelli, founder of Kernel Labs and co-host of Latent Space podcast, walks us through two very different AI workflows: (1) a fully autonomous coding setup using OpenAI Symphony + Linear, where...

6 Heinä 35min

Sonnet 5 review: I ran 64 generations to find out if it's worth it

Sonnet 5 review: I ran 64 generations to find out if it's worth it

I’ve been testing every major frontier model release since the start of the year, and when Anthropic dropped Sonnet 5, I wanted more than a vibe check. I got tired of one-off tests I couldn’t repeat o...

30 Kesä 25min

No Figma. No Jira. No docs. How Gusto built a new product line with Claude Code | Eddie Kim (CTO)

No Figma. No Jira. No docs. How Gusto built a new product line with Claude Code | Eddie Kim (CTO)

Eddie Kim is the co-founder and CTO of the payroll and HR platform Gusto, which just crossed $1 billion in revenue and serves more than 500,000 small businesses. Recently he did something most CTOs do...

29 Kesä 51min

GLM 5.2: why I’m replacing Opus in Claude Code with this new model

GLM 5.2: why I’m replacing Opus in Claude Code with this new model

I put GLM 5.2, the open-weight coding model from Z.AI, through four real tasks inside my actual codebase: a codebase architecture audit, a UI redesign, and a 45-minute autonomous bug-hunting session p...

24 Kesä 27min

How Claude Mythos found a 15-year-old bug in Mozilla Firefox | Brian Grinstead

How Claude Mythos found a 15-year-old bug in Mozilla Firefox | Brian Grinstead

Brian Grinstead is a distinguished engineer at Mozilla, where he’s worked on Firefox and the web platform since 2013 (he joined to help launch Firefox DevTools). Recently he and his team pointed an ag...

22 Kesä 48min