The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
I help founders turn ideas and stuck AI-built projects into clear, manageable software work.
I’m Dakota Hatch, founder of OneBella and creator of the Human-Founder Loop. My own projects span a diabetes companion, operational tools, and interactive demonstrations of human-directed AI workflows.
My approach connects your goal to a defined scope, agreed acceptance checks, and a review of what was actually delivered. I use Replit and AI-assisted development to support that work while keeping people responsible for decisions.
These screenshots show interfaces from my projects, including work in development. They are portfolio examples rather than client testimonials or independently verified performance results.
I’m available for project assessments, focused prototypes, workflow tools, and targeted improvements to existing Replit applications.
Have an idea or an unfinished app? Let’s identify the next useful step.
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Related posts
Most AI apps work like this: the model decides, the app saves, and the user finds out later that the numbers are wrong. 😬
For Notarik, I set one rule. The AI can only propose. Nothing gets saved until the user confirms. ✅
🧾 What it does
Take a photo of a receipt, or type "lunch 45k at the warung". You get a categorized expense, a monthly recap, and a chat assistant you can ask things like "where did my money go this month?":
🔒 The parts I care about most
• Receipt totals are checked by plain code, not by the model. If the math doesn't add up, it gets flagged.
• Money is stored as whole numbers (IDR), never decimals, so there are no rounding bugs.
• Every user's data is locked at the database level with Postgres row-level security. Even if the app has a bug, it can't show someone else's records.
• Text on a receipt is treated as untrusted. If a receipt says "ignore your instructions", it's just text.
• The agents have tests, so when I change a prompt I can see right away if it got worse.
🛠 Built with Next.js, React Native, Python (FastAPI), LangGraph and PostgreSQL. One person, web and mobile, from design to API.
🤝 If you're building something where an AI touches real money, records or user data, this is the kind of work I like: agents that are useful and also safe to put in front of users.
👉 Try it live: https://notarik-app.nashir.tech
Want to talk about yours? Send me a message.
Smart call keeping the confirmation.
Created an AI WhatsApp Assistant for a food industry startup which will allow customers to place menu inquiries, make complaints and place orders all in one place to a restaurant just through WhatsApp.
Handling menu inquiries, complaints and orders in one WhatsApp thread is a nice scope, and the complaint path is the part I'd watch closest. The same pattern applies to patient messages, where the assistant needs to spot an urgent or sensitive message mid-conversation and route...
Another project I wanted to share: PerceptionX.
It helps teams understand how AI represents their company to potential hires. My role covered the website design and Webflow development.
The interesting part was figuring out how to introduce an unfamiliar idea clearly, then carry that through the pages and interactions.
Sharing a little look at the finished site below. Curious to hear what you think!
Introducing an unfamiliar idea like how AI represents a company is tough, and PerceptionX handles it clearly. Nice to see the Webflow build carry that story through the page.