At a glance
WHAT IT’S REALLY ABOUT
Non-coder builds retro AI hardware projects using Cursor agents fast
- Maddie describes going from feeling excluded from coding to rapidly building hardware-software projects after discovering AI tools like Lovable and Cursor.
- She demos a “Print Me a Message” system where anyone submits a web form and a Raspberry Pi sends the message to a tiny thermal receipt printer on her desk, with logging to a database for reliability.
- She explains the constraints of modern pager infrastructure—one major remaining network and outdated vendor workflows—and shows a multi-hop workaround to route Twitter events to a pager via Cloudflare Workers, Resend, and Gmail.
- The “personal API” project reframes social thoughtfulness as a machine-readable interface, letting others (or future agents) query preferences like coffee orders, pets, restaurants, and scheduling context.
- Across projects, her workflow emphasizes brainstorming in Cursor’s clean agent view, buying hardware only after “trust but verify” double-checks, and aiming for delight rather than strict practicality.
IDEAS WORTH REMEMBERING
5 ideasAI tools can collapse the gap between idea and hardware reality for beginners.
Maddie starts with a plain-language goal, has Cursor interview her to clarify requirements, then iterates into a concrete build plan and shopping list—making hardware projects feel accessible even without deep coding fluency.
Design for “delightful physical touchpoints,” not just digital utility.
The receipt-printer messages and pager notifications create tangible, playful interactions that strengthen connection with an online community, even when the implementation is intentionally “impractical but fun.”
Reliability improves when you log inputs even if the last-mile device fails.
Her printer flow records every “Print Ticket” submission in a database even if the printer is down, which helped when the always-on printer eventually broke and she needed a history of attempted messages.
Legacy networks require workaround thinking—and AI makes the glue code cheap.
Because the pager’s email gateway is restrictive and outdated, she chains services (Cloudflare Worker → Resend → Gmail → pager email) to bridge modern APIs to retro infrastructure without hand-writing every integration detail.
Use “trust but verify” when AI recommends hardware purchases.
Unlike software, wrong parts create real cost and delay, so she repeatedly asks the model to double-check edge cases (compatibility, cables, protocols) and catches errors before ordering.
WORDS WORTH SAVING
5 quotesI've always felt jealous of people who could code, and then when I finally was able to kind of join that world, I just started thinking, "What else was inaccessible to me that's completely accessible now?" And hardware was one of those things.
— Maddie Reese
Honestly, through my dad. Um, my dad introduced me to Lovable about a year ago. He's been really into AI for a while, and he goes, "Hey, did you know this, this is possible now?"
— Maddie Reese
I just wanted some way to interact with people that was kind of more physical, because everyone that I had been talking to about these kind of things, I, I knew online.
— Maddie Reese
Kind of like how growing up in San Diego, you kind of, you pick up a little bit of Spanish and can kind of understand it, but you can't, like, really speak it. That's kind of where I'm at with code right now.
— Maddie Reese
And what I love about your approach is saying, like, "I don't care if it's n-" Like, of course it's not practical to, like, send it to Cloudflare and then Resend, and then proxy it through a Gmail, and then send it to the official... Like, of course that's not practical. But guess what? It's fun. It's fun.
— Claire Vo
High quality AI-generated summary created from speaker-labeled transcript.
