FynX

FynX-Your entire financial operating system, automated.

Comment

The Problem We Couldn't Ignore

Pakistan has 65 million people using digital banking. 5.2 million small businesses contributing 40% of GDP. And almost none of them have real visibility into their own money.

We watched freelancers, shopkeepers, and factory owners abandon every finance app within weeks because typing every transaction by hand just doesn't stick. Banks reject 70–80% of SME loan applications not because the businesses aren't viable , they can't prove their cash flow. No record. No history. Nothing. That's what FynX started from.

What We Built

FynX is an AI-powered financial operating system — two apps sharing one Gemini intelligence layer.

FynX Personal reads incoming bank SMS alerts in the background and logs every transaction automatically. Zero manual entry. The Gemini-powered Co-Pilot generates a real-time Financial Health Score from 0 to 100, forecasts month-end spending, detects forgotten subscriptions, and answers financial questions from actual user data.

FynX Business gives Pakistan's 5.2 million MSMEs their first real financial infrastructure — automated accounting, inventory, HR, payroll, and CreditIQ, an alternative credit scoring engine:

$$\text{CreditIQ} = 0.35 \cdot \text{CF}{\text{consistency}} + 0.25 \cdot \text{SR}{\text{rate}} + 0.25 \cdot \text{VPR} + 0.15 \cdot \text{Activity}$$ Business owners can ask "Can I afford to hire someone next month?" and get a data-backed answer through Gemini function calling.

How We Built It

Flutter for Android and iOS. Firebase for backend and real-time sync. Google Gemini API with multi-model fallback across three variants and exponential backoff for 99% AI availability. Google ML Kit for on-device OCR. Android BroadcastReceiver for background SMS parsing across HBL, Meezan, UBL, MCB, Bank Alfalah, and EasyPaisa. Hive for offline caching. Clean Architecture with BLoC state management.

Challenges We Faced

Pakistani bank SMS formats are inconsistent - three different formats from Bank Alfalah alone. We built a pattern library with manual correction fallback. Voice tracking accuracy dropped on Urdu-English mixed input how most Pakistanis actually speak. We fixed this by prompting Gemini to handle code-switched language explicitly. CreditIQ prompt engineering took 30 iterations before Gemini produced reliable, explainable scores in strict JSON schema.

What We Learned

Alternative credit scoring from behavioral transaction data works. Early testers with zero formal credit history got CreditIQ scores matching our manual assessment of their financial health.

For a country where most small business owners are invisible to formal credit bureaus, that result matters more than the app itself. Gemini function calling turned FynX from a ledger into an advisor.

Built With

Share this project:

Updates