3
1 Comment

A bioinformatics degree was supposed to be my answer. Five weeks before graduation, I'm betting on something else.

I picked bioinformatics at UCSD because it was the top-ranked major and I wanted to contribute to science one day. Four years later, my peers are all queueing up for PhDs to break into biotech, and I'm realizing I don't want to spend another half-decade learning before I'm 'allowed' to make something. So I'm using my last 5 weeks of college to ship. First product: Notie (https://notieapp.com), an AI-native study app for students.

The spark came from a small thing I noticed last semester. Every time I read a paper, I'd highlight a confusing paragraph, copy it, switch tabs to ChatGPT, paste it, ask my question, read the answer, switch back to the PDF, scroll to find where I was, lose three minutes, repeat. Twenty times an hour. By the end of an evening I had a chat history full of detached questions and no idea which paragraph any of them came from. The flashcards I tried to make from those answers were even worse — 'explain this concept' with no link to the page or paper that prompted the question. Two weeks later I'd review the card and have no idea what context I needed to even understand it.

The original product idea actually came from my mentor at Novartis, where I noticed researchers had a specific ritual for going through papers: they'd highlight interesting passages and pull them into slide decks for their own work. I started building Notie with that professional workflow in mind, but as I talked to more peers, I realized the pain was sharper in the student space. Apps like Notability and GoodNotes treat AI as a support character — a little 'explain this' button, or tack-on gimmicks like 'quiz me' that don't map to how people actually study. Nobody had built a note-taking app where AI was the main character. So I pivoted.

The core insight is that students shouldn't have to tab-switch between their PDF and ChatGPT. The reading and the thinking should live in the same place. So in Notie, you import a PDF and highlight passages directly — text or even a region around a figure or chart — and the AI conversation is anchored to whatever you highlighted, with full context of the document already loaded. Responses cite back to specific pages like [p.4] so you can click and jump straight to the source. From those highlights, you can auto-generate flashcards , and the flashcard remembers which highlight, which page, and which document it came from. Three weeks later when you review the card, you can click straight back to the paragraph that originally prompted it. The connection between question, answer, and source never breaks.

There's also a global Ask AI bar that searches across every PDF and note in your library at once. So when you remember reading something a few weeks ago in some paper but can't remember which one, you ask, and Notie pulls the actual excerpts from the right paper(s) with citations. That cross-document recall was the feature that genuinely changed my study habits — it removed the 'where did I read this' tax that was making me re-read instead of synthesize. And because of where the idea started, export-to-pptx is in there too, for anyone who wants to turn their highlights into a deck.

The bigger vision is an ecosystem for studying where AI organizes the material and you do the thinking. I'm building this as a web app, not iPad-first, because every student has a laptop and not every student has an iPad. Honestly, I think trying to replicate pen and paper on glass is a losing game. Pen and paper is irreplaceable for working through problems, and laptops are unbeatable for organizing knowledge. Notie leans into that split rather than fighting it.

It's free while I iterate. Eventually I want to do a subscription with tiered plans based on AI token usage. I have at least two more ideas I want to build after this one.

Two asks. Try it (https://notieapp.com) and tell me what's broken, or any feature that would actually improve how you study. And if you've shipped something to prove a point to yourself, comment and let's connect. I want to learn from your scars.

on May 11, 2026
  1. 1

    This is a strong lesson because the product didn’t win by becoming more technical. It won by making the first successful outcome obvious. For infrastructure products, that first few minutes matters a lot because users are not only judging features, they are judging whether they can trust the tool to work without fighting it.

    The “first delivered email as fast as possible” framing is probably the real conversion lever. SMTP credentials, live logs, SPF/DKIM/MX checks, and one-click test email all reduce the anxiety that usually comes with email infrastructure.

    One thing I’d watch longer term is the KingSMTP name. It explains the category clearly, but it also keeps the product locked inside a narrow SMTP utility frame. If this expands into broader transactional email infrastructure, delivery intelligence, or developer-first messaging ops, a cleaner infrastructure-grade brand like Exirra.com would age better.