From zero coding background to hardware hacker: How Cursor + a Raspberry Pi makes AI fun
· Summarized
Key takeaways
- Building hardware projects can be accessible and fun by combining AI with physical devices, even if you lack formal coding skills.
- Using tools like Cursor’s agent view helps in the brainstorming, planning, and verification phases of hardware projects, making complex ideas more manageable.
- Building for fun and experimentation often leads to innovative and unique devices that foster human connection, like message printers and personal APIs.
- It's okay to take unconventional, circuitous routes in hacking legacy systems or outdated technology—imperfect, playful hacking can lead to delightful results.
- Approaching AI troubleshooting with questions and verification, rather than frustration, encourages growth and learning, making the process enjoyable rather than frustrating.
Summary
Maddie's Journey into Hardware and AI Fun
The episode begins with Maddie Reese sharing her story of transitioning from a lack of coding confidence to becoming an avid hardware hacker. Inspired by her dad's introduction to Lovable, Maddie immersed herself in hardware projects, blending her love for AI with physical devices. She discusses her approach to project development—using Cursor's agent view to brainstorm, plan, and verify parts before purchase. Maddie's work includes creating a thermal receipt printer that accepts messages globally, a personal API for sharing details like coffee orders, and a Twitter pager that uses a Raspberry Pi. Her philosophy emphasizes building for fun, not practicality, which fuels her creativity and innovation.
Building Interactive Hardware Projects with AI
Maddie describes her creative process of merging hardware with AI, such as her thermal printer connected via Bluetooth to a Raspberry Pi, which allows people worldwide to send messages. She emphasizes brainstorming with Cursor, asking questions about project requirements, and triple-checking before making purchases. Her projects include a digital messaging device using outdated paging technology and a personal API that consolidates information like pet details and favorite snacks. Maddie sees AI as a tool for fun and connection, turning physical objects into interactive touchpoints that foster human interaction.
The Philosophy of Fun and Imperfect Engineering
Throughout the conversation, Maddie advocates for building projects for fun rather than practicality, embracing the imperfect, experimental nature of hardware hacking. She shares her willingness to explore non-conventional setups, like multiple steps to hack a legacy pager network, because the joy and creativity behind these experiments outweigh strict practicality. She also discusses her approach to troubleshooting AI failures—asking the AI to double-check its work, understanding that her knowledge is growing, and viewing mistakes as part of the learning journey. Her attitude encourages a playful and curious approach to technology.
Future Hardware Dreams and Creative Ideas
Maddie fantasizes about her dream hardware: a dot matrix banner printer, which she envisions using to print large banners for meetings. She discusses her fascination with retro hardware, inspired by projects that combine nostalgic tech with modern AI. She also explores new ideas like printing banners or quotes at meetings, and creating playful, physical displays of digital content. Maddie’s ongoing projects demonstrate her passion for merging the old with the new, using AI not just as a tool but as a catalyst for creative expression.
Sponsors
- FireCrawl · If you're building with AI agents, you've probably hit the same wall. Your agent needs data from the web, but the right pages are difficult to find, varied in JavaScript or blocked behind logins. FireCrawl is a web data API that lets agents search, scrape, and interact with the web at scale. And get that clean, structured data they can actually use. Over a million developers, including myself, build on it. It's open source and it's free to start. Stop fighting the web for data and start powering your AI agents and apps with FireCrawl. at firecrawl.dev. Use code howiAI to get 10,000 free credits today.
- CustomerIO · You're here because you'd rather use AI than talk about it. With CustomerIO, you describe the campaign you want to build and the AI agent creates for you. The audience, the messages, and the timing. You review it, make any changes you want, and watch. Instead of spending hours stitching together tools and workflows, you can focus on the work that actually drives growth. Every campaign is tied back to results, so you can see what's working and what to do next. More than 9,000 brands use customer IO to turn the data they already have into messages customers remember, visit customer.io slash howiAI to try it today.
Show notes
Maddie Reese is a vibe coder, hardware tinkerer, and builder. She builds things at the intersection of software and hardware, including a thermal receipt printer that people around the world can message directly, a fully functional Twitter pager running on a Raspberry Pi, and a personal API that tells you her coffee order so you don’t have to ask. Maddie approaches hardware the same way she approaches software: dump the idea into Cursor, let it interview her, get a shopping list, triple-check the parts before buying, and build. She got her start after her dad introduced her to Lovable, and she locked herself in her room and didn’t come up for air.
What you’ll learn:
- How Maddie built a thermal receipt printer that accepts messages from anywhere in the world using a Raspberry Pi and Bluetooth
- How to use Cursor’s agent view to brainstorm a hardware project
- What belongs in a personal API and why agents, not just humans, will be the ones using it
- How to read just enough code to do some damage, without needing to understand all of it
- Why building for fun, not practicality, is the fastest path to actually shipping physical projects
—
Brought to you by:
Firecrawl—Power AI agents with clean web data
Customer.io—Build customer engagement campaigns from a single prompt
—
In this episode, we cover:
(00:00) Intro
(02:00) Maddie’s AI pill moment
(03:53) The thermal receipt printer: live demo and how it works
(11:10) The pager project
(17:23) Why she uses Cursor’s clean agent view instead of terminals and browsers
(19:05) The personal API: coffee order, pets, favorite snacks, and more
(22:57) Lightning round and final thoughts
—
Tools referenced:
• Cursor: https://www.cursor.com/
• Lovable: https://lovable.dev/
• Raspberry Pi: https://www.raspberrypi.com/
• Resend: https://resend.com/
• Cloudflare Workers: https://workers.cloudflare.com/
• Supabase (Conduct database referenced): https://supabase.com/
• Twitter/X API: https://developer.x.com/
• Spoke pager network: https://www.spoke.com/
• OpenClaw: https://openclaw.ai/
—
Where to find Maddie Reese:
Website: https://maddiedreese.com
Message her directly: https://maddiedreese.com/message
—
Where to find Claire Vo:
ChatPRD: https://www.chatprd.ai/
Website: https://clairevo.com/
LinkedIn: https://www.linkedin.com/in/clairevo/
—
Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email jordan@penname.co.
Follow this show on AudioBrevity and new episodes get summarized for you. Create a free account