SmartWalt

Hey Indie Hackers! 👋 I am adding SmartWalt to the directory today and wanted to share the core problem we are tackling.

In personal finance apps, there is a massive friction point: you either spend 10 minutes a day manually typing out your expenses, or you surrender your highly sensitive bank login credentials to a syncing API like Plaid. For privacy-conscious users—or global users outside the US—the latter simply isn't an option.

So, we decided to use AI to bridge the gap. We built SmartWalt to give users the speed of automated syncing combined with the absolute privacy of manual entry.

The AI Features we built to replace bank-syncing:

• 🎙️ Voice Spend Tracking: Users can simply open the app and say, "Lunch $12." The AI instantly extracts the amount, assigns the correct category, and logs the date.

• 📸 Instant Receipt OCR: Snap a photo of any physical receipt, bill, or invoice. The AI reads the vendor, amount, and date in under 3 seconds, eliminating manual data entry.

• 🤖 Walt AI Coach: A built-in conversational financial assistant that monitors spending velocity, provides real-time budget warnings, and offers personalized insights.

Under the Hood: To make this fast enough that users actually prefer it over bank-syncing, latency had to be practically zero. We are running a Flutter mobile frontend connected to a FastAPI backend. The AI orchestration is handled by LangGraph and custom OCR pipelines running securely on AWS.

I’d love to hear from other builders here: Are any of you currently using AI to replace traditional third-party API integrations? How are you keeping your latency down when running multi-step AI workflows?

Hey Indie Hackers! 👋

We just hit a major milestone with SmartWalt: we finally built and deployed our in-app referral system.

Up until now, our growth on Android has been entirely organic. But as we prepare for our upcoming iOS launch, we knew we needed a structured product-led growth loop to help lower our CAC and turn our early adopters into advocates.

Here is how we structured it: We went with a milestone-based approach. For every friend a user invites who successfully signs up, the referrer earns 10 days of free Pro access. They can stack these rewards up to 90 days (3 full months).

To make it as frictionless as possible, we:

• Built an interactive horizontal milestone tracker right into the user profile so they can visualize their progress.

• Integrated native sharing sheets so users can instantly blast their custom promo codes via WhatsApp, SMS, or Telegram with pre-filled text.

It’s exciting to finally have this live, but it was definitely a learning curve getting the reward logic and tracking dialed in.

I’d love to hear from anyone else who has built a referral system from scratch. Did you find that capping the rewards (like our 90-day limit) helped create urgency, or did it disincentivize your super-sharers?