MakanMate

Inspiration

MakanMate was inspired by a common experience at hawker centers where choosing what to eat becomes difficult, especially when trying to meet calorie goals, increase protein intake, or avoid certain ingredients. Seeing how often people rely on guesswork made us want to create a more helpful and personalized solution.

What it does

MakanMate is an AI companion that helps users make better food choices at hawker centers. Users can ask questions about calories, protein content, dietary suitability, or allergens, and receive instant recommendations. The chatbot is represented by a customizable 3D avatar to make interactions feel more natural and engaging.

How we built it

We built MakanMate as a mobile application with a chatbot trained on common hawker food knowledge. Since many hawker dishes are similar across stalls, the system can provide general nutritional guidance. User preferences and chat history are stored to allow more personalized responses over time, while the 3D avatar enhances the conversational experience.

Challenges we ran into

One major challenge was the lack of standardized nutritional data for hawker food. Another challenge was designing the chatbot to be helpful without overwhelming users with too much information. Balancing accuracy, simplicity, and user experience required multiple iterations.

Accomplishments that we're proud of

We are proud of creating an AI companion that feels approachable and practical in a real-world setting. Integrating personalization and a 3D avatar into the chatbot helped make the experience more engaging than a typical text-based assistant.

What we learned

Through this project, we learned how to design an AI solution around a real user problem rather than just technical features. We also gained insights into user experience design, personalization, and the challenges of working with imperfect real-world data.

What's next for MakanMate

In the future, we plan to improve nutritional accuracy, expand support for more dietary needs, and add location-based hawker recommendations. We also aim to enhance the AI companion’s conversational abilities to provide even more personalized guidance.

Built With

• azure
• javascript
• openai
• python