Claude Code for normal people: skills, voice mode, and how to collaborate with AI

August 10, 2026

AI Summary

5 min read

Grace Clark spent her first two hours with Claude Code doing exactly one thing: yapping. She opened the terminal, talked for two or three minutes about the problems in her consulting business—the deluge of emails, the friction of client onboarding, the 20 open tabs and 20 hours a week on admin—and let Claude figure out what to do. That rant became a pipeline operator that now runs her business. The lesson she now teaches is that prompt engineering is dead; what matters is intent engineering, and the best way to get there is to stop writing hyper-engineered chunks of text and start having a three- or four-minute conversation that lets the model extract the prompt from you.

The three-step skill-building process

Behind every polished output Clark shows her students—a branded, password-protected interactive proposal, a custom onboarding questionnaire, a rebuilt Gmail client—is the same three-step process. First, document your standards. For Clark, that means a voice guide (a "think like me" guide that captures her philosophy of communication, words she uses and avoids, and how she makes decisions) and a clear explanation of what a given deliverable means to her business. Second, put it on a timer—her pipeline operator wakes up every hour to check where clients are and move them through stages. Third, publish everything to Netlify so the output is live and interactive.

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

Never miss an episode of How I AI

Get every new episode summarized in your inbox — free, ~5 minutes to read.

No spam. Unsubscribe anytime.

What you'll learn

1 (00:00) **Prompt Engineering vs. Intent Engineering** - Grace introduces the core philosophy shift from hyper-engineered prompts to conversational intent.
2 (02:06) **Sponsor: Bolt.new** - Brief ad break for the AI app builder.
3 (03:07) **The Problem: Email Deluge and Lost Personalization** - Grace explains the core business problems that drove her to build AI tools.
4 (04:49) **The Pipeline Operator: The Core Product** - Grace's most impactful AI tool that runs her business.
5 (06:43) **See the Magic: From Skill File to Client-Facing HTML** - A live demonstration of the output of Grace's system.
6 (09:00) **Driving AI Adoption: Lead by Example** - How to convince teams to use AI by demonstrating its value.
7 (10:15) **Building the Muscle: The Two-Step Adoption Method** - The practical steps to get people to default to using AI.

+ Full timestamped outline available in the app

Show Notes

Grace Clarke is an AI educator and former marketing consultant who taught herself Claude Code earlier this year and built a curriculum out of the process. She now runs her entire service business on tools she’s built with Claude, including a pipeline operator, a proposal maker, and a Gmail replacement she created in under 30 minutes, and teaches individuals and teams to do the same.

What you’ll learn:

How to build an hourly pipeline in Claude that moves clients through your process automatically
Why Grace ditched traditional proposals for password-protected, interactive HTML documents built in Claude
How she uses a “voice guide” skill file so every Claude output sounds like her, not like AI slop
The two-step forcing function she teaches non-technical clients to build the muscle of opening Claude
Why she started building in Claude Code, then handed the work off to Cowork via a Markdown session file
How she replaced Gmail entirely with a custom inbox
Why she teaches “intent engineering” instead of prompt engineering, and what that looks like in practice
How she uses Claude on her phone, on walks, to track workouts and manage plants alongside client work

—

Brought to you by:

Bolt.new—Turn your idea into a real product

Hyperagent—Deploy fleets of agents that handle real work

—

In this episode, we cover:

(00:00) Grace’s background and why she started building with Claude

(04:48) The pipeline operator: what it is and how it runs her business every hour

(08:48) Building the muscle memory to use AI

(12:02) What goes into building a skill file (voice guide, proposal rules, versioning)

(13:50) How she built her proposal maker

(16:15) The voice guide: teaching Claude how she thinks, not just how she writes