Inspiration
It started with something small.
Sodas kept showing up again and again on receipts. One of us spotted the pattern while looking through past purchases. Individually, each purchase felt insignificant. Together, they revealed something bigger. The spend added up quickly, but more importantly, it reflected an everyday habit that had gone largely unnoticed.
That raised a question: what other patterns are hidden in the things we buy?
Most finance apps tell you how much you've spent. We wanted to understand what people are repeatedly buying and what those purchases say about their habits.
That insight led to Buyopsy.
What it does
Buyopsy is an AI-powered app that turns receipts into behavioural insights.
Users can scan a receipt and automatically extract information such as the shop, items purchased and total spend. The app then analyses that data to surface patterns and habits.
Examples include:
- 19 coffees this month
- Most purchases happen between 8am and 9am
- You buy snacks on 74% of your evening shopping trips
The goal is simple: help people better understand their spending behaviour through the purchases they make every day.
How we built it
Before building, we spoke to potential users and ran a survey to understand how people currently track spending, what frustrated them about existing tools, and whether behavioural insights would actually be useful.
As a team, we combined product, design and technical expertise throughout the process. We mapped user journeys, designed the experience, prioritised features and iterated quickly based on feedback.
We used AI-assisted development tools, primarily Lovable, to move rapidly from idea to implementation. This allowed us to focus on validating the concept and refining the user experience rather than spending weeks building infrastructure from scratch.
Challenges we ran into
The biggest challenge was deciding what not to build.
We generated a lot of ideas, including budgeting features, shopping lists, recommendations and spending targets. It was tempting to keep adding functionality.
Instead, we focused on one question:
“Does this help users understand their behaviour better?”
That helped us prioritise receipt scanning, data extraction and insight generation over a larger feature set.
Accomplishments that we're proud of
We're proud that we went from an idea to a working product in a short amount of time.
More importantly, we're proud that Buyopsy doesn't stop at scanning receipts.
The application can already:
- Extract purchase data from receipts
- Store purchase history
- Generate behavioural insights from real purchases
The moment we saw a receipt turn into "19 coffees this month" was the moment the product started to feel real.
What we learnt
One of the biggest things we learnt is that people don't necessarily want more financial data.
They want insights that feel meaningful and relevant to their lives.
Through user research and testing, we also learnnt that the most interesting part of the product wasn't spending totals or budgets. It was helping people spot patterns they hadn't noticed before.
Small purchases may seem insignificant in isolation, but over time they often tell a much bigger story.
What's next for Buyopsy
The current version focuses on turning receipts into insights.
Next, we want to make those insights smarter and more personalised.
We're exploring:
- Habit tracking over time
- Purchase predictions
- Restock reminders based on buying patterns
- A conversational AI experience where users can ask questions about their spending habits
For example:
"Based on your purchase history, you'll probably need milk in the next 2 days."
Our long-term vision is to help people understand not just where their money goes, but the habits behind it.
Built With
- chatgpt
- github
- lovable
- novus
Log in or sign up for Devpost to join the conversation.