Higher Education Category Submission

689 – AI ChatBot

In this project, I developed an AI-based chatbot application focused on helping students with their educational queries. The app is built using Flutter for cross-platform support and integrates Gemini AI APIs to handle the conversation and generate smart, relevant answers. The main idea was to create a learning tool that is available anytime and can assist students in understanding different topics without needing a teacher present.

The design is kept simple and user-friendly so that students from different backgrounds can easily use it without technical knowledge. From a technical side, the project uses API integration to connect the app with Gemini’s AI services, ensuring the chatbot provides accurate and helpful responses in real-time.

This project shows how AI can be used practically in education, giving students instant access to information and learning support. The chatbot can make a big difference, especially for students who don’t have easy access to teachers or extra learning resources. It also highlights how modern apps can combine mobile development and AI technologies to solve real-world problems in education.

The idea for this project came when I noticed that a lot of students, including myself and my friends, often struggle to find quick help when studying, especially after school hours. Most of the time, textbooks and online materials don't give the exact answers we’re looking for, and it’s not always possible to reach out to teachers or tutors. This made me realize there’s a real need for a tool that can support students instantly whenever they get stuck. Since AI technology has become so advanced recently, I thought it would be a smart solution to use it for creating a chatbot that can answer academic questions in real time and make learning easier and faster for everyone.

To build my project, I used Flutter to create the mobile app because it’s easy to build for both Android and iOS from one codebase. For the AI part, I integrated Gemini APIs to handle the chatbot conversations. This way, I didn’t have to train any complicated AI models myself — I could focus more on building a working app. The main resources I needed were a laptop for development, a good internet connection, and access to the Gemini API platform. These were enough for me to complete the project.

To check if there’s real demand for this idea, I looked at how many students today rely on quick Google searches, YouTube videos, or AI tools like ChatGPT when studying. It’s clear that students want fast, simple answers without wasting time, and an educational chatbot fits that need perfectly.

The main features of my app are:

Students can ask academic questions directly through the app.

The chatbot gives real-time, AI-generated answers.

A clean and simple chat interface that’s easy to use even for younger students.

To make sure users have a good experience, I focused on keeping the app fast, lightweight, and easy to navigate. I avoided adding too many buttons or confusing options. For performance, I plan to measure things like how fast the chatbot responds, how many users keep using the app, and feedback from real users to see what can be improved.

The app’s architecture is simple. I used Flutter for building the mobile app and connected it to Gemini AI APIs to handle the questions and answers. When a user types a question, it’s sent to the API, and the reply is displayed instantly in the chat. This setup keeps the app lightweight and fast.

To implement the main features, I first made sure the API integration was working correctly. After that, I focused on designing a clean, easy-to-use chat interface. I kept the app simple to make sure students can quickly find answers without any confusion.

The development took about a month:

First week: Planning and setting up the project.

Second week: Building the basic app and API connection.

Third week: Designing the chat screen and improving UI/UX.

Fourth week: Testing and fixing bugs.

For performance, I will measure:

How fast the chatbot responds.

How many users return to use the app again.

Direct feedback from users about their experience.

Flutter helps with creating a smooth interface, and Gemini APIs handle the AI responses. Both work together to give students quick, helpful answers with a good user experience. So far, the app has been working smoothly without big issues.

My idea is innovative because it combines the power of AI with mobile technology to provide instant academic support, something that traditional learning resources or even regular apps don’t offer in a personalized way. Instead of searching through long articles or videos, students can simply ask a question and get a direct, understandable answer within seconds.

What makes the project creative is the way it uses existing AI technology (Gemini APIs) inside a lightweight, student-friendly mobile app built with Flutter. I didn’t try to build a complicated system — I focused on making something that students could actually use easily in real life, at any time they need help. The design is simple and fast, so even students with low-end devices or limited internet can benefit from it.

By combining a smart AI backend with an easy front-end experience, the app bridges the gap between information and accessibility. This creative approach directly addresses the biggest challenge students face: getting fast, reliable help when they need it most.
Innovation here isn’t just in the technology — it’s in making the technology usable, accessible, and genuinely helpful for students in their daily learning.

To make sure the app can handle more users over time, I plan to use scalable backend services. Since the AI processing happens on Gemini’s cloud servers, the app itself stays light and doesn’t need heavy resources on the device. If user demand grows, I can easily upgrade the API subscription or switch to higher-capacity cloud services without changing the app itself. I will also monitor app performance closely to spot and fix any speed or server issues early, avoiding bottlenecks.

For environmental sustainability, the app is designed to be lightweight, which means it uses less battery and mobile data. By relying on cloud services that invest in green data centers, the project also indirectly supports lower energy consumption.

To keep users engaged for the long term, I plan to add features based on feedback, like saving favorite answers, adding voice input, or offering study tips through the chatbot. The app’s simple and flexible design makes it easy to update without needing a full rebuild.
As users' learning needs evolve, I can quickly adjust the app by updating the AI prompts or adding new educational categories, keeping the app relevant and useful.

My solution focuses on making quality educational support available to everyone, not just those who can afford private tutoring or expensive resources. Many students, especially in underserved or rural areas, struggle to get quick academic help when they need it. By providing an AI-powered educational chatbot for free (or at a very low cost), the app promotes greater equity in learning and helps bridge the gap between students with different levels of access to support.

The app is simple to use, designed for students from different backgrounds, and doesn’t require high-end devices or fast internet. This focus on accessibility and inclusion ensures that more students, regardless of their location or financial situation, can benefit equally from the service.

To measure the social impact, I plan to track:

The number of active users from different regions.

User feedback, especially from students in low-access areas.

Improvement in users' study satisfaction through optional surveys.

I will also stay responsive to the evolving needs of the community by regularly collecting feedback inside the app and updating the chatbot’s capabilities to cover a wider range of academic topics or support different languages in the future.
The goal is not just to provide answers, but to empower more students to learn confidently, no matter where they are.

Personal Information Collection Statement (PICS):
1. The personal data collected in this form will be used for activity-organizing, record keeping and reporting only. The collected personal data will be purged within 6 years after the event.
2. Please note that it is obligatory to provide the personal data required.
3. Your personal data collected will be kept by the LTTC and will not be transferred to outside parties.
4. You have the right to request access to and correction of information held by us about you. If you wish to access or correct your personal data, please contact our staff at lttc@eduhk.hk.
5. The University’s Privacy Policy Statement can be access at https://www.eduhk.hk/en/privacy-policy.

• I have read and agree to the competition rules and privacy policy.