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

Key takeaways

Traditional prompt engineering is becoming obsolete; focus should shift to intent engineering—clearly defining the desired outcome for AI to act upon.
Building custom AI workflows and tools (pipeline automation, proposal generation, Gmail replacement) can significantly enhance business productivity and customer experience.
Cultivating the habit of defaulting to AI through reminders, documenting SOPs, and chaining skills is key to widespread adoption.
Understanding and teaching the technical foundations (like chaining skills, versioning, custom connectors) empowers users to create practical, automated solutions.
Adopting AI is accessible to non-technical users—start simple with prompts like 'rebuild Gmail' and iterate based on results.
The future of AI workflows is about collaboration, intent clarity, and chaining interconnected skills rather than static prompts.

Summary

The Shift from Prompt Engineering to Intent Engineering

Grace Clarke emphasizes that traditional prompt engineering is becoming obsolete; instead, the focus should shift toward intent engineering—crafting clear intentions for AI to act upon. She advocates for creating interactive, context-rich artifacts that can be password protected and that facilitate seamless collaboration with AI, moving away from static prompts to Conversational workflows that are more natural and effective.

Building Practical AI Tools for Business and Personal Use

Grace demonstrates how she has built and integrated various AI-driven solutions into her workflow, such as an hourly pipeline operator that automates client processes, a proposal generator using interactive and branded HTML, and a Gmail replacement built in under 30 minutes. She showcases her approach of using Claude Code and Cowork to develop these tools, underlining the importance of custom connectors, versioning, and maintaining a clear structure like voice guides and rule files. Her focus is making AI accessible and practical for everyday business challenges.

Strategies for Cultivating AI Adoption and Muscle Memory

Grace shares techniques to help individuals and organizations build the habit of using AI. Key tactics include setting reminders to prompt AI engagement, building collaborative workflows, and teaching the underlying technical concepts to increase confidence. She highlights the importance of showing rather than telling—demonstrating high-quality, personalized outputs using AI— and cultivating muscle memory to automatically default to AI tools for repetitive or complex tasks.

Personal Use Cases and Mindset Shift

Beyond professional workflows, Grace discusses personal applications such as workout and plant tracking, emphasizing that AI can simplify life by consolidating diverse activities into one interface. She addresses misconceptions around AI adoption, stressing that it’s not about prompts but about collaboration and building new habits. Her approach is to be direct and sometimes blunt when prompting AI—yelling or being assertive—because it aligns with her work ethic and belief that AI can handle high-level, complex tasks once properly guided.

Technical Foundations and Future of Workflow Automation

Grace walks through how she built her AI tools, starting from basic connections and custom plugins to complex chains of skills involving Claude Code, markdown files, and cloud deployment. She stresses the importance of documenting SOPs and chaining skills logically to create automated workflows. Her strategy involves starting simple—like replacing Gmail through iterative prompts—and expanding as confidence and need grow, viewing prompt engineering as dead, replaced by intent engineering and workflow chaining.

Tips for Overcoming Barriers to AI Adoption

Grace identifies common misconceptions—especially that technical skills are required—that hinder wider adoption. She advises beginners to just start with simple prompts, like 'I hate Gmail, rebuild it,' and iteratively improve from there. She advocates for creating regular habits (e.g., taking screenshots and asking Claude for help) and normalizing AI use through consistent practice. Her overarching message is that anyone can implement these tools easily if they focus on intent, habits, and concrete outputs.

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