DEV Community: Yanina Trekhleb

I found my "Magic Wand": Building a Private, Zero-Dependency Journaling PWA 🪄

Yanina Trekhleb — Sun, 22 Mar 2026 04:53:40 +0000

For years, I’ve had ideas that fizzled out during the "which framework should I use?" phase. I’d get stuck in the setup, and the spark would die. This week, everything changed. I stopped overthinking and went back to the basics.

I built Daily Reflections—a private, offline-first journaling space—using 100% Vanilla JS. No React, no build steps, just pure flow.
The Solution: A Local-First Architecture 🏠
I decided to build a PWA that treats the browser as the destination, not just the interface.

State & Persistence: Everything lives in localStorage. There is no backend. Privacy isn't a feature; it's the architecture.

Zero Dependencies: I challenged myself to skip the heavy libraries.

Charts: Built using the Canvas API (no Chart.js).

Icons: Hand-drawn Inline SVGs to keep the app lightweight and "analog."

Offline-First: A simple Service Worker and Web App Manifest make it fully installable on iOS and Android. It works perfectly at 2 AM in airplane mode.

Feature Highlight: "Then vs. Now" 🕰️
I’m a data person, so I wanted to see my progress. The app automatically resurfaces entries from exactly 1 week, 1 month, or 1 year ago. It’s incredible how much perspective you gain just by reading what "Past You" was worried about seven days ago.

Lessons Learned 🎓
Going "Vanilla" felt like finding a magic wand. Without the abstraction of a framework, I felt closer to the code and finished the MVP in record time.

Check out the live project: https://yaninatrekhleb.com/daily-reflections/

I’d love to hear from other devs—have you experimented with "No-Cloud" or local-first tools lately? How do you handle the 5MB localStorage limit for long-term data?

webdev #javascript #showdev #pwa #claudecode

How I Built a Full-Stack AI App in Under a Week — As an Email Developer

Yanina Trekhleb — Wed, 18 Feb 2026 19:28:43 +0000

TL;DR: I'm an email developer who had an idea for 2 years, couldn't afford engineers, and used Claude Code to build a live product with AI vision, payments, and real users in less than a week.

The Idea That Wouldn't Go Away

For 3+ years, my entire world was HTML tables, inline CSS, and making buttons render in Outlook. I've built over 3,000 email templates. I know what mso-line-height-rule: exactly does. That's the kind of developer I am + a passionate food blogger.
But I had this idea that kept nagging me.
Every week, the same thing happened in my kitchen: I'd buy fresh herbs, vegetables, ingredients for recipes I was definitely going to make. By Friday, half of it was wilting in the back of my fridge. The parsley died. Again.
I wanted an app where I could just photograph my fridge and get instant recipe suggestions — prioritized by what's about to expire. No barcode scanning. No typing expiration dates. One photo.
For two years, this idea lived in my head. I looked into hiring developers. The quotes made me close my laptop and walk away. As a solo creator, it felt impossible.

The "Why Not" Moment

Then I tried Claude Code with a Max subscription.
What happened next is honestly still hard to believe. In under a week, I went from idea to a live, deployed, payment-processing product.
Here's what I built:
✋Don't Touch It! — Snap your fridge, get recipes sorted by what expires first.
Live at: https://dont-touch-it-app.vercel.app/

The Tech Stack

Layer	Tool	Why
Framework	Next.js 14 (App Router)	SSR, API routes, everything in one repo
Database	Supabase (PostgreSQL)	Free tier, auth built-in, real-time
AI	Claude Vision API	Best image understanding I tested
Payments	Stripe	One-time credit packs, webhooks
Hosting	Vercel	Auto-deploy from GitHub, PWA support
Styling	Tailwind CSS	Fast iteration, mobile-first

Total monthly cost to run: ~$120 (API budget + subscription). Everything else is on free tiers.

How the AI Magic Works

The core feature is deceptively simple:

User uploads a fridge photo
Claude Vision API identifies every visible ingredient
AI estimates perishability for each item (days until it should be used)
Ingredients get color-coded: 🔴 use today, 🟡 use this week, 🟢 no rush
Recipes are generated prioritizing the most perishable items

The tricky part was prompt engineering. My first attempts identified maybe 50% of visible items. After iteration, I got it to scan every shelf, drawer, door compartment, and even partially hidden items. A well-stocked fridge now returns 15-25 identified items.
The perishability estimation was another rabbit hole. Getting AI to accurately know that fresh basil lasts 2-3 days while eggs last 3 weeks — and everything in between — required very specific prompting.

The Hardest Parts (That Nobody Warns You About)

Webhooks in Production Testing Stripe webhooks locally with the CLI? Easy. Getting them to work reliably in production? I lost an entire afternoon. The signing secret alone had me questioning my career choices.
Image Handling on Mobile Phone cameras produce massive images. Uploading a 4MB photo over a cellular connection is painful. Compression, resizing, format handling — this was way more work than I expected.
Environment Variables I had 15+ env vars by the end. Keeping local, test, and production variables in sync — and remembering which Stripe keys are test vs live — nearly broke me.
The Hat-Switching Tax The hardest part wasn't any single skill. It was switching between them 15 times a day:

9 AM: debugging a Stripe webhook
10 AM: picking a button color
11 AM: writing Instagram copy
12 PM: restructuring a database table
1 PM: filming my fridge with the cat in the background

Each context switch costs brain power. By day 4, I was running on coffee and stubbornness.

Monetization: Keeping It Simple

I didn't want subscriptions for v1. Too complex, too much commitment for users.
Instead: credit packs.

Pack	Price	Per Scan
3 scans	$0.99	$0.33
10 scans	$2.49	$0.25
15 scans	$3.99	$0.27

Everyone gets 3 free scans per day. Power users can buy more.

What I'd Do Differently

Start with the webhook setup — Don't save payments for last. Set up Stripe, webhooks, and credit logic early.
Mobile-first from day one — 90% of users will be on their phone. I caught layout issues late that could've been avoided.
Prompt engineering deserves its own sprint — The AI prompt is the product. Treating it as an afterthought was a mistake.
Ship the ugly version faster — I spent too long on button colors when I should've been validating the concept.

The Numbers (Week 1)

Development time: ~6 days
Total cost: $120 (API credits + subscription) + $0 (all free tiers)
Lines of code: I honestly don't know, Claude Code wrote most of it
My contribution: product vision, design decisions, prompt engineering, and a lot of debugging, marketing, social media engagement.

Try It

🍳 https://dont-touch-it-app.vercel.app/
3 free scans every day. Works on any phone or computer.
If you're an email developer, a designer, a marketer, or anyone who thinks "I'm not a real developer" — you can build products now. The barrier has never been lower.
And if you've ever thrown away forgotten parsley — this app is for you.

I built a bread baking schedule app in 3 hours with Claude Code — without writing a single line of code

Yanina Trekhleb — Thu, 15 Jan 2026 04:48:04 +0000

The Problem
I got into sourdough baking recently. If you've tried it, you know — it's a 20-hour process with a lot of waiting and precise timing.
Feed your starter. Wait 5 hours. Mix the dough. Wait 30 minutes. Add salt. Fold every 30 minutes for 2 hours. Shape. Proof overnight. Bake in the morning.
Every time I baked, I'd set a dozen phone alarms and still miss steps. I wanted a simple app that would calculate all the timestamps for me.
I know frontend development, but the thought of spending weeks building all the logic kept stopping me.
Then I tried Claude Code.

The Build Process
I just talked to Claude like I was a client describing what I wanted:
"I want a bread baking schedule app. I pick a recipe, set my start time,
and it shows me all the steps with exact timestamps."
Within seconds — a working React app.
Then I kept iterating:

"Add a dropdown with different recipes" → Done
"Show ingredients for each recipe" → Done
"Let me set the END time and calculate backwards" → Done
"Deploy it to GitHub Pages" → Done

Each request took seconds. No Googling. No Stack Overflow. No debugging missing semicolons.
Total time: 3 hours of conversation.
(Okay, plus waiting for rate limits to reset 😅)

The Result
Flour Hour — a bread baking schedule planner with:

📋 22 recipes — sourdough, croissants, brioche, focaccia, bagels, cinnamon rolls, discard pancakes, and more
⏰ Flexible scheduling — set start time OR work backwards from when you want to eat
📝 Ingredient lists — for each recipe
📱 Mobile-friendly — works on any device

Tech Stack

React + Vite — frontend framework
GitHub Pages — free hosting
Google Analytics — tracking visitors

And I didn't write a single line of code myself.

What Surprised Me

It understood context I didn't have to explain everything each time. Claude remembered what we'd built and made changes in the right places.
It handled the boring stuff Deployment configs, CSS path issues, file structure — Claude just handled it.
It felt like collaboration I'd describe a problem, and Claude would sometimes suggest a better approach than what I had in mind.

Try It
🔗 Live app: https://yaninatrekhleb.github.io/flour-hour/
💻 GitHub: https://github.com/YaninaTrekhleb/flour-hour

If you've been sitting on an app idea because the technical work feels overwhelming — try just talking to Claude about it.
You might surprise yourself.

Follow me for more:

📸 Instagram
📺 YouTube
🎵 TikTok
☕ Buy me a coffee

What are you building with AI? Drop a comment — I'd love to see!

To-do list - helpful or disappointing?

Yanina Trekhleb — Thu, 30 Apr 2020 17:26:37 +0000

Do you like to write down your plans for the day? Do you like to plan for tomorrow or the week ahead?

For me it's easier to live if I know what I'm gonna do today, and also so I don't forget anything!😀
Also, I know there's no point in writing down more than 10 tasks, it'll be depressing if you don't finish them in time.
And you don't want to plan anything else. You don't have to push yourself, you have to help yourself.
Start with five important things for a day!

I have combined practicality, ease of use, and I think a beautiful design and created To Do List and I've open-sourced it on GitHub.

What about you? Does planning ahead help you?

👉🏻Try it here👈🏻

10 000 days Birthday Calculator

Yanina Trekhleb — Tue, 14 Apr 2020 13:38:11 +0000

Have you ever wondered how many DAYS you are? And what about when is your ’10 000 days Birthday’?
Maybe it’s time bake a birthday cake? 😀

So I decided to create a "10 000 days birthday calculator" and I've open-sourced it on GitHub.
Just choose your birthday date and see when it’s time to celebrate!
You can also see how many days you are today and at what stage in life you are!

👉🏻Try it here👈🏻

235 ideas of what to do while you are on quarantine

Yanina Trekhleb — Mon, 13 Apr 2020 20:02:20 +0000

So far, like everyone else sitting in quarantine, I’ve been thinking about doing something useful (like everyone is doing 😄) at home.

I started googling and found a lot of ideas to do something with your loved one or alone while you’re at home.

So I decided to create a "random generator" of activities which you can do during the quarantine and I've open-sourced it on GitHub.

You will get ideas from such categories as: movies, creativity, personal development, cooking, cleaning, and much more.

Meet dawn, clean up the pantry, spend five minutes in silence and more.
What will you get from this list?

Do some little challenge.Choose 3–5 consecutive actions and do their next days.Or choose 3 actions for 1 day. The choice is big.

👉🏻Try it here👈🏻