Creating no-code apps is easier than ever. Here are my takeaways from using Cursor + Claude + Figma to build an app to track savings goals in Bitcoin terms.

Pt. 1: Product development process

☞ START WITH DESIGNS. Before saying a word to our friend Claude, I recommend spending time up front to think through your desired pages, information hierarchy, UX flow, and basic designs. In general, prompting with visuals and text will get you closer to your desired end state than text alone. When you’re ready, lay out your screens in Figma, save each as a PNG file, and add them to Cursor so that you can reference them in your initial prompt to the AI.

☞ WAIT TO WORK ON THE BACKEND. To reduce complexity, start by asking the AI to build out the front end, informing it you’ll work on any backend elements later. Just tell it to leave placeholders or use dummy data.

☞ WORK ITERATIVELY ON BIG CHANGES. The bigger the change, the greater the risk. Claude’s biggest mistakes seem to come from either lacking context (see “Context is king”) or trying to be too helpful (e.g., adding features you didn’t ask for). Do less, Claude. Give the AI a shorter leash. If you want to allow users to update the icon associated with an expense, you might give it the following prompts in succession: create the “Update icon” button, link it to an empty “Icon Library” page, layout the icons in a grid with a “Save button”, and – finally – update the icon across the app when a user clicks “Save”.

☞ BONUS: DON'T TRY TO USE VOICE. I saw a post on X that made the a voice + AI workflow look effortless. As a result, I spent $20 on a license for this dictation software. In practice, it doesn’t work well. Given the time it takes to turn your voice to text, you’re better off typing short instructions. For longer instructions, specificity is super important – as you’ll see below. Talking at your computer ≠ precise prompting.

If you're looking for a fun project this weekend, and you want to get better at working with generative AI, try building a no-code app.

☞ DOWNLOAD CURSOR: https://www.trycursor.com/
Cursor is a code editor. It has a premium AI feature called Composer, which can look over your codebase and write new code when prompted. Your download comes with a free 2-week trial. Cmd+I brings up Composer.

☞ DOWNLOAD FIGMA: https://www.figma.com/downloads/
Figma is the most popular tool for creating user interfaces. The Figma Community has tons of free templates for website, apps, etc. that you can use as a starting point: https://www.figma.com/community.

☞ DOWNLOAD XCODE (if you’re building an iOS or macOS app): https://developer.apple.com/xcode/
While Cursor is used for the actual coding, Xcode is needed for building, testing, and deploying apps on Apple's platforms.

The high-level workflow is…
1. In Figma, design the app / feature in Figma
2. In Cursor, prompt Composer to build the app / feature by writing acceptance criteria and referencing uploaded PNGs of your designs
3. In Xcode, recreate the file structure from Cursor, then copy and paste the code to duplicate the code that’s in Cursor (I’m sure there’s a better way to do this. If you’re an engineer, please teach me!)
4. Build the app in Xcode. Review the changes.
5. Repeat – starting from 1 or 2 as needed.

This is insane. Without writing a line of code, I created an app to track your savings goals in Bitcoin terms just by prompting Claude. It's very similar to collaborating with an engineer, but the feedback/iteration cycles are WAY faster.

This took me ~20 hours over 1.5 weeks with lots of lessons learned. The next project will probably go 50% faster.

My takeaway is that – for many business ideas – non-technical founders can now build a MVP on their own. They can test, learn, iterate, and validate product-market fit on their own. Then – when it comes time to scale – build out an engineering team. What do y'all think?

*taptaptap* Is this thing on? 🎤 👈