Inspiration
Growing up, my dad's government job took us to small towns every three years. Unfortunately, these places lacked good schools and passionate teachers. I never felt curious about studying, and my grades suffered. Things changed when we moved to a city for my 11th grade. Suddenly, I had teachers who cared, tried to ignite curiosity about their subjects, and my interest in academics soared—I even scored a 4 GPA in 12th.
This experience made me realize the vast gap in education, especially in rural areas where most Indians live. About 70% of the country resides there, but many lack good teachers. Surprisingly, almost everyone has smartphones. We want to change things. Our app aims to spark curiosity among kids in these neglected areas. It's not just about better grades; it's about helping teachers teach better and keeping parents in the loop about their child's education. This startup is our way of making a real impact and bridging the educational gap for kids across the nation.
What it does
AI-Powered Text Interaction: Dive into Indian school course books, engaging with them like never before. Utilize OpenAI's assistant to ask questions, request summaries, explanations, self-assessments, and more.
PDF Superpowers: Seamlessly upload personal PDFs, unleashing the power of OpenAI's chat completion AI. Explore features like summarization, questioning, and other intelligent operations.
Topic-Based Learning: Enter specific topics, and watch as our AI generates structured questions. Enhance your skills by answering each question, guided by OpenAI's teaching prowess.
Voice Interaction: Every message is equipped with a text-to-speech button, utilizing Azure Speech Service for immersive audio experiences. Additionally, enjoy the convenience of speech-to-text, allowing seamless conversion of spoken words into written text.
What it will do
Personalized Learning Paths
- Analyze students' strengths and weaknesses.
- Create personalized learning paths with tailored resources.
Smart Content Generation
- Generate up-to-date and engaging educational content.
Automated Grading
- Implement automated grading systems for assignments.
AI-Enhanced Assessments
- Design adaptive assessments based on skill levels.
AI-Enhanced Feedback
- Provide constructive feedback on assignments and creative work.
Language Learning Assistants
- Offer real-time feedback on pronunciation and grammar.
Accessibility Features
- Enhance accessibility with text-to-speech, speech-to-text, etc.
Data Analytics
- Analyze student data for insights into learning patterns.
Emotional Support Chatbots
- Provide emotional support and guidance to students.
Adaptive Learning Platforms
- Adapt content and difficulty levels based on performance.
Language Translation Tools
- Integrate AI-driven translation tools for non-native speakers.
Early Warning Systems
- Identify students at risk and provide timely interventions.
Mentorship and Career Guidance
- Offer AI-powered advice for informed career decisions.
How we built it
Tech Stack Overview
Our application, built with Next.js 13, React-Query, and TypeScript, delivers a seamless user experience. Tailwind CSS enhances styling, while Prisma ORM connects to PostgreSQL for efficient data handling.
- trpc (Typed RPC): Ensures type-safe APIs, providing reliability in communication.
- PostgreSQL: Our reliable and scalable database solution.
- Azure Services: VMs, Azure SQL Data, BlobStore, and Text-to-Speech (TTS).
- OpenAI APIs: Power the Assistant API, Chat Completion API, and Embeddings API.
- Pinecone: Optimizes vector data storage and retrieval.
- Langchain: Streamlines development with abstractions.
Challenges we ran into
Never having used Next.js, TypeScript, React-Query, trpc, and Azure before, my journey with these technologies was quite a ride. Most of my time went into reading docs, debugging type errors, and streaming texts or audios with Next.js backend and trpc. Handling PDFs seemed like a big task at the start. I didn't have my credit card for Azure, so I had to use a friend's. Prompt engineering more like banging head against a wall.
Accomplishments that we're proud of
Learning new tech and implementing it while our minds were cluttered with what to build first. Many aspects need improvement in the built features, but we're committed to fixing them.
What we learned
While building the app, I learned about trpc, Next.js, TypeScript, and also got into Azure and OpenAI services. Azure's cool AI stuff like live chat avatars, speech checks, translation, personal voice, and audio tricks became part of our app, changing how we do things in education. The idea to make the whole app friendly for audio came to me as I played around with these features. Working with Azure AI not only boosted my tech skills but also gave me lots of new ideas and things to try.
What's next for Aintrest
We plan launch the MVP before March. We're set to partner with a small school, offering them our platform for free to refine our product in real-world settings. The big picture? A complete school solution platform. Before march, we'll try to secure some funds via jobs, Hackathon win, or explore fundraising if possible.
Log in or sign up for Devpost to join the conversation.