Campus Go AI

Dharshini Thirri — Fri, 16 Oct 2026 10:33:18 +0000

🚀

Your Campus. Your World. One App.

Project Title: AI-Powered Offline Student Companion and Smart Campus Assistant

Domain: Artificial Intelligence, Education Technology, Career Development, and Smart Campus Solutions

Target Users: Students aged 15 and above

Core Idea: One intelligent platform to support students in learning, career growth, opportunity discovery, and campus life.

🌟 1. Project Overview

CampusGo AI is an AI-powered student companion designed to make academic life easier, smarter, and more organized.

Today, students use different applications and websites for studying, finding courses, searching for internships, discovering hackathons, learning new technologies, and accessing campus services. Switching between so many platforms takes time and makes it difficult to keep track of important information.

CampusGo AI aims to bring these student needs together in one application.

The platform combines a locally running AI assistant with educational support, career guidance, opportunity discovery, and campus-related services. It follows an offline-first approach, meaning that selected features can continue working without an internet connection after the required software, AI model, and resources have been installed or downloaded.

When internet connectivity is available, the application can also be extended to retrieve updated information from suitable external services.

🎯 Our vision

To build a smart digital companion that helps every student learn better, develop valuable skills, discover opportunities, and manage campus life from one convenient platform.

💡 Why is this project important?

Students need more than just an AI chatbot. They need a connected system that helps them understand what to learn, decide what to do next, discover opportunities, and access useful resources.

CampusGo AI aims to connect these activities instead of treating them as separate tasks.

🛑 2. Problem Statement

Students often face difficulties accessing reliable study materials, understanding complex academic concepts, identifying skill gaps, finding suitable career paths, and discovering opportunities such as internships, jobs, hackathons, workshops, and online courses.

These resources are distributed across different websites and applications. As a result, students must search through multiple platforms, manually organize information, and independently decide which learning activities are relevant to their goals.

Students may also struggle to connect academic learning with real-world career requirements. For example, a student interested in artificial intelligence might not know which programming languages to learn, which projects to build, or which competitions could provide practical experience.

Another challenge is internet dependency. Students with slow or unreliable internet connections may find it difficult to access online learning resources and AI-powered assistance consistently. Privacy can also be a concern when personal questions or learning information are sent to external services.

Campus-related information introduces additional difficulties. Students may need separate applications to explore campus facilities, find food options, understand transportation services, and stay informed about events.

Therefore, there is a need for a unified, intelligent, and privacy-conscious student platform that connects academic assistance, personalized skill development, career guidance, educational opportunities, and campus services while supporting selected offline functionality.

CampusGo AI proposes a solution to these challenges through a single, student-focused application.

🎯 3. Project Objectives

The main objective is to simplify students' academic and campus experiences through accessible AI assistance and organized information.

Our specific objectives are:

📚 Improve learning: Help students understand concepts through simple, personalized explanations.
🤖 Provide offline AI assistance: Support selected AI tasks locally without requiring continuous internet access.
🧭 Guide career development: Help students understand which skills and projects are relevant to their career interests.
🔍 Improve opportunity discovery: Bring internships, jobs, hackathons, workshops, and courses into one organized experience.
🧠 Support skill development: Recommend useful learning activities and practical projects.
📍 Simplify campus discovery: Help students access campus location and service information.
🤝 Encourage collaboration: Create opportunities for peer learning, team formation, and project collaboration.
🔐 Protect privacy: Minimize unnecessary collection and sharing of student information.
🔔 Improve organization: Support reminders for deadlines, events, and learning goals.
🌐 Reduce fragmentation: Make student-focused services easier to access from one interface.

⚠️ 4. Existing System and Its Limitations

Students already have access to learning platforms, AI chatbots, job portals, mapping applications, and event websites. These tools can be useful, but they often serve separate purposes.

Common limitations

📱 Too many applications: Students must switch between different platforms to complete related tasks.
🔎 Scattered information: Finding relevant and trustworthy information can take time.
🧩 Disconnected learning and careers: Students may learn concepts without knowing how those skills connect to jobs or projects.
⏰ Missed opportunities: Students may overlook deadlines when announcements are spread across multiple channels.
📶 Internet dependency: Some online services become unavailable when connectivity is poor.
🔒 Privacy concerns: Certain AI services process user prompts on remote servers.
🏫 Fragmented campus information: Events, facilities, food, and transportation information may be available through different channels.

Why do we need CampusGo AI?

CampusGo AI aims to connect these activities through a common interface. Instead of searching independently for every need, students can begin with one application and access relevant assistance or resources.

It is not intended to replace every existing platform. Its purpose is to make student support more organized, convenient, and accessible.

💙 5. Proposed Solution

CampusGo AI proposes an intelligent student companion built around local AI, a simple web interface, and modular application features.

The solution has two operating modes.

📴 Offline mode

After the necessary software, AI model, and resources have been installed or downloaded, selected features can work without an active internet connection.

Examples include:

Asking the local AI model general study questions.
Generating basic career guidance through the local application.
Accessing previously downloaded learning materials, once local resource storage is implemented.

Importance: This approach can improve accessibility for students who experience unreliable internet connectivity and can reduce the need to send AI prompts to a remote model service.

🌐 Online mode

When an internet connection is available, future integrations can provide current information about opportunities, courses, maps, campus events, and external services.

Importance: Students need current information for deadlines, applications, navigation, and services that change frequently.

The application should clearly distinguish live information from saved information and demonstration data.

⭐ 6. Important Features and Why They Matter

📚 Feature 1: AI Study Buddy

What is it?

The AI Study Buddy is a conversational learning assistant that helps students understand academic concepts, ask questions, and explore difficult topics in simpler language.

How does it work?

The student enters a question in the application.
The frontend sends the question to the backend.
The backend forwards the request to the locally running AI model through Ollama.
The model generates an answer.
The backend returns the answer to the interface.
The student reads the explanation and can ask another question.

Example: A student asks, “Explain machine learning in simple words.” The assistant can provide an introductory explanation and examples.

Why is this feature important?

Helps students understand difficult concepts.
Provides another way to learn outside classroom hours.
Encourages students to ask questions without hesitation.
Can make technical subjects more approachable.
Supports learning even when cloud AI services are inaccessible, provided the local model is running.

Future improvement: Add PDF uploads, class-note search, practice questions, and source-linked answers so students can learn directly from their study materials.

🧭 Feature 2: AI Career Guidance and Skill Roadmap

What is it?

This feature helps students explore possible career paths based on their interests and current skills.

How does it work?

The student enters their skills and interests.
The backend processes the submitted information.
The application generates a structured roadmap or career suggestions.
The student receives suggested learning topics and project ideas.
The student can use the roadmap to plan their next learning activities.

Example: A student interested in web development could receive a suggested learning sequence:

HTML → CSS → JavaScript → Frontend Frameworks → Backend Development → Databases → Git and GitHub → Projects.

Why is this feature important?

Helps students understand what to learn next.
Connects academic knowledge with practical skills.
Makes career preparation more structured.
Encourages project-based learning.
Helps beginners explore careers without needing to know every technology in advance.

Future improvement: Personalize roadmaps using learning progress, completed projects, and verified skill requirements from relevant job descriptions.

🏆 Feature 3: Jobs, Internships, and Hackathons

What is it?

A centralized opportunity discovery module intended to help students find internships, entry-level jobs, hackathons, workshops, and competitions.

How should it work?

Collect opportunities from approved or reliable sources.
Organize them by category, skills, location, eligibility, and deadline.
Allow students to filter relevant opportunities.
Display the official application link and important dates.
Support optional reminders before deadlines.

Why is this feature important?

Students can discover opportunities that match their interests.
Reduces the effort required to search multiple websites.
Encourages participation in practical learning and competitions.
Helps students connect their skills with real-world experience.
Can improve awareness of internships and career-building activities.

Important implementation note: The current prototype uses sample event data. Live job and hackathon discovery requires real data sources or suitable integrations. Sample listings must not be presented as verified opportunities.

🧠 Feature 4: Learning Resources and Technology Updates

What is it?

A module intended to help students discover courses, tutorials, documentation, study resources, and relevant technology developments.

How should it work?

Organize resources by topic and skill level.
Let students search for a subject or technology.
Recommend relevant resources based on their interests.
Provide links to original educational materials.
Allow selected resources to be saved for later offline access.

Why is this feature important?

Encourages continuous learning beyond classroom lessons.
Helps students explore emerging technologies.
Reduces time spent searching for suitable resources.
Supports self-paced learning.
Helps students prepare for projects, internships, and hackathons.

Where Wikipedia or other third-party content is used, the application should provide attribution and links to the original sources.

📍 Feature 5: Campus Discovery and GPS

What is it?

A feature intended to help students access campus location information and, in a future version, navigate to useful facilities.

How should it work?

The student chooses to use the location feature.
The browser requests permission to access location.
If permission is granted, the application receives the available coordinates.
A future mapping integration can display nearby facilities and directions.

Why is this feature important?

Helps new students become familiar with a campus.
Can make facilities easier to find.
Supports campus discovery.
Can reduce confusion when locating classrooms, libraries, laboratories, and other facilities.

Important implementation note: The current prototype can request browser geolocation and display coordinates. Coordinates alone are not an interactive map or navigation system. Maps, campus locations, and directions require additional integration.

🍱 Feature 6: Food and Transportation Services

What is it?

A campus services module intended to organize information about food options and transportation services.

How should it work?

Display available service information.
Let students explore food options or transportation details.
Provide relevant prices, availability, or provider information when verified data is available.
In a future version, connect to authorized providers where appropriate.

Why is this feature important?

Makes common campus-related information easier to access.
Helps students explore available services.
Reduces the need to search through separate channels.
Can make the overall campus experience more convenient.

Important implementation note: The current prototype contains sample food information and demonstration ride information. Real ordering, booking, payments, and ride tracking require additional services and security controls.

🤝 Feature 7: Student Collaboration

What is it?

A proposed module for helping students connect around shared learning goals, projects, and hackathon participation.

How could it work?

Students identify their interests and skills.
They discover relevant project groups or learning communities.
They can share resources or coordinate project tasks.
Suitable collaboration tools can support team communication and progress tracking.

Why is this feature important?

Encourages peer-to-peer learning.
Helps students build teamwork and communication skills.
Supports project development.
Can help students find teammates for hackathons.
Encourages students to learn through shared experiences.

This feature requires additional development, including appropriate access controls, privacy protections, and moderation.

🔔 Feature 8: Notifications and Reminders

What is it?

A proposed system for reminding students about deadlines, events, learning goals, and other important activities.

How could it work?

The student selects an opportunity or learning goal.
The application records the reminder preference.
The system checks the relevant date or schedule.
It provides a reminder through an appropriate notification mechanism.

Why is this feature important?

Helps students organize their activities.
Reduces the chance of forgetting important deadlines.
Encourages consistent learning habits.
Helps students plan around events and applications.

Saved local reminders can be designed to work offline. Notifications about newly published external opportunities require internet connectivity or another update mechanism.

🔐 Feature 9: Privacy-Conscious Local AI

What is it?

CampusGo AI uses a locally hosted model for selected AI tasks rather than requiring every prompt to be sent to a cloud AI service.

How does it work?

The user enters a question.
The backend sends the request to the local Ollama service.
The local model generates a response.
The application displays the result.

Why is this feature important?

Reduces the need to transmit AI prompts to a remote model provider.
Can support AI assistance without continuous internet connectivity.
Gives the developer greater control over the local inference workflow.
Supports a privacy-conscious design.

Local AI does not automatically guarantee complete privacy. External integrations, browser permissions, logs, and stored data must also be managed carefully.

🛠️ 7. Technology Stack and Its Importance

Each technology has a specific role in making the application work.

Technology	Purpose	Why it matters
HTML	Structures the webpage	Creates the application interface
CSS	Styles the interface	Makes the application clear and attractive
JavaScript	Handles interactions	Connects user actions with backend requests
Python	Implements application logic	Powers the backend functionality
FastAPI	Provides API endpoints	Connects the frontend with application services
Uvicorn	Runs the web server	Makes the backend accessible locally
Ollama	Runs a supported AI model locally	Enables local AI inference
Gemma 3 1B	Selected language model	Generates responses to AI requests
Git	Tracks code changes	Helps manage and review development
GitHub	Hosts the source repository	Supports sharing, collaboration, and version history
`.venv`	Isolates Python packages	Helps avoid dependency conflicts

🧩 How the technologies work together

The frontend collects the student's input. The FastAPI backend receives the request and determines which operation is required. For an AI question, the backend communicates with Ollama, which runs the selected local model. The backend then returns the response to the browser.

For non-AI features, the backend may return application data or communicate with an integrated service.

🏗️ 8. System Architecture

The application can be understood as five connected layers.

Layer 1: Frontend 🎨

The frontend is what students see and interact with. It includes the dashboard, forms, navigation, and feature interfaces.

Importance: A clear interface makes the application easier for students to use.

Layer 2: Backend ⚙️

The backend receives requests, validates inputs, manages application logic, and returns responses.

Importance: It connects the interface to the AI model and other services while keeping the application logic organized.

Layer 3: Local AI 🧠

Ollama runs the selected language model locally and provides responses to AI requests.

Importance: It enables selected AI features without requiring a remote model API for every request.

Layer 4: Local Resources and Data 💾

This layer can store saved learning materials, configuration, and application data. A future version can introduce a database and a searchable document index.

Importance: It supports access to saved resources and can provide a foundation for offline learning.

Layer 5: Online Integrations 🌐

External services can provide verified opportunity listings, maps, and other current information.

Importance: It allows the application to offer information that cannot reliably be generated from a local language model alone.

🔄 Complete request flow

Student → Frontend → FastAPI Backend → Local AI or Relevant Data Source → Backend Response → Frontend → Student.

👩‍💻 9. Complete Development Process

This section explains how we build the project from an empty folder to a working application.

Step 1: Identify the problem 💡

We first identify the difficulties students face in learning, career preparation, opportunity discovery, and campus activities.

Importance: A clearly defined problem helps us develop features that solve real student needs instead of adding technology without a purpose.

Step 2: Define the solution and requirements 📝

We decide which features belong in the first version and which can be developed later.

For the initial prototype, we focus on the dashboard, local AI chat, career roadmap endpoint, sample events, campus coordinates, and demonstration services.

Importance: Defining the minimum viable product helps us build and test the core application before adding complex integrations.

Step 3: Set up the development environment 💻

We create the project folder in Visual Studio Code and set up Python and a virtual environment.

The .venv environment keeps the project's Python dependencies separate from other Python projects on the computer.

Importance: A properly configured development environment makes the project easier to run, maintain, and troubleshoot.

Step 4: Organize the project files 📂

The initial project structure is:

main.py — contains the backend application and API endpoints.
requirements.txt — lists the required Python packages.
.gitignore — identifies files Git should ignore.
README.md — explains the project and how to run it.
static/index.html — contains the initial browser interface.

Importance: Organizing files makes the project easier to understand, debug, and expand.

Step 5: Develop the backend ⚙️

We use Python and FastAPI to create the application's endpoints.

The backend handles incoming requests and returns responses for available features.

Importance: A backend allows the frontend to communicate with AI services and application data through a structured interface.

Step 6: Develop the frontend 🎨

We use HTML, CSS, and JavaScript to create the dashboard and feature interactions.

The frontend sends requests to the backend and displays the responses.

Importance: The frontend turns the underlying code into a usable application that students can interact with.

Step 7: Configure the local AI model 🤖

We install Ollama, download the selected model, and test it independently before connecting it to the application.

The selected model is Gemma 3 1B, subject to compatibility and performance on the development computer.

Importance: Testing the model independently helps us distinguish AI configuration problems from application bugs.

Step 8: Integrate AI with the backend 🔗

We connect the backend to the local Ollama API. When a student asks a question, the backend forwards it to the model and returns the answer.

Importance: Integration turns a standalone local AI model into an AI feature within CampusGo AI.

Step 9: Integrate the available features 🧩

We connect the dashboard to the relevant backend endpoints and test the initial features.

Sample data must be clearly identified, and future integrations must be added for live opportunities, interactive maps, and real campus services.

Importance: Integration ensures that the different parts of the application work together rather than existing as disconnected pieces.

Step 10: Run the application locally ▶️

We install the required Python packages and start the FastAPI server.

The browser then accesses the application through the local server address.

Importance: Running the application locally allows us to test it before publishing the source code.

Step 11: Test and debug 🐛

We check whether the homepage loads, the AI responds, the career endpoint works, and the other available features return the expected results.

If something fails, we inspect the error message, identify the cause, correct it, and test again.

Importance: Testing helps detect errors before the project is demonstrated to judges or shared with other developers.

Step 12: Review privacy and security 🔐

We check for hardcoded API keys, passwords, and other sensitive information. We also review .gitignore and verify which files Git is tracking.

Importance: Publishing secrets can expose accounts or services to unauthorized access. A repository should contain the code needed to run the project, not private credentials.

Step 13: Use Git and GitHub 🌐

Git tracks the changes made to the code, while GitHub hosts the repository online.

After testing and reviewing the files, we commit the source code and push it to GitHub.

Importance: Version control helps preserve the development history, supports collaboration, and makes it easier to share the project with mentors and judges.

Step 14: Prepare the final demonstration 🎤

We demonstrate the working application, explain the problem it solves, show the architecture, and discuss the implemented features and future enhancements.

Importance: A clear demonstration helps judges understand the project's practical value, technical approach, and potential impact.

🧪 10. Testing and Validation

We need to verify the application rather than assume it works.

Functional testing

Does the homepage open correctly?
Does the AI Study Buddy return a response?
Does the career endpoint generate a roadmap?
Does the events endpoint return the expected sample data?
Does geolocation behave correctly when permission is granted or denied?
Are demonstration services clearly labelled?

Integration testing

Does the frontend communicate with FastAPI?
Can FastAPI reach the local Ollama service?
Does the application handle an unavailable model or server?
Are invalid or empty inputs handled appropriately?

Offline testing

Does the local AI feature work after the model is downloaded and the required services are running?
Does the application distinguish saved information from current online information?
Does the application communicate clearly when an external service is unavailable?

Security testing

Are API keys and passwords absent from committed source files?
Does location access require permission?
Are user inputs validated?
Do error messages avoid exposing secrets?

Testing principle: We will report only the results that we actually observe. Performance statistics and claims of successful offline operation must be verified before they are included in the final submission.

🔐 11. Privacy, Security, and Responsible AI

CampusGo AI is intended to be privacy-conscious and suitable for a student audience.

Our design principles include:

Process suitable AI requests locally whenever possible.
Request only the permissions needed for a feature.
Avoid collecting unnecessary personal information.
Keep private credentials out of source code and GitHub.
Use appropriate authentication and access controls before adding student accounts.
Clearly explain when information is sent to an external service.
Provide sources for important educational and opportunity-related information.
Recognize that AI-generated answers can be inaccurate.
Add suitable moderation and reporting controls before enabling student communities.

Why is this important?

Students should be able to use educational technology with a clear understanding of how their information is handled. Responsible design builds trust and reduces avoidable privacy and security risks.

Local AI can reduce external data transmission, but the entire application still requires careful security and privacy practices.

✨ 12. Innovation and Uniqueness

CampusGo AI focuses on bringing several connected student needs into one platform.

🚀 What makes the idea valuable?

1. Local AI assistance

Selected AI tasks can run on the student's computer, reducing reliance on a remote model service.

2. Learning-to-career connection

The application aims to connect study activities with skills, projects, and career preparation.

3. Unified student experience

Academic assistance, opportunity discovery, and campus information are organized around the needs of students.

4. Offline-first design

Selected functions and previously downloaded resources can remain available without continuous internet connectivity.

5. Modular architecture

The backend can be extended with document search, verified opportunity sources, mapping services, and other integrations over time.

6. Privacy-conscious approach

Local processing and minimal data collection can reduce unnecessary exposure of student information.

These are the project's intended differentiators. Their practical effectiveness must be demonstrated through implementation and testing.

📌 13. Current Implementation and Future Development

It is important to distinguish what is prepared in the prototype from what still needs to be built.

Feature	Current status
Browser dashboard	Initial interface prepared
Local AI chat	Backend integration prepared; needs execution testing
Career roadmap	Basic endpoint prepared
Events	Sample data
Campus GPS	Browser coordinates, with permission
Food services	Sample menu
Ride services	Demonstration information
PDF Q&A with citations	Future development
Live jobs and hackathons	Future integration
Interactive maps and routes	Future integration
Student accounts and database	Future development
Collaboration and notifications	Future development

🛣️ Future development roadmap

Phase 1 — Working prototype: Run and test the current application, fix errors, and improve the interface.

Phase 2 — Smarter learning: Add PDF processing, document retrieval, and source-linked answers.

Phase 3 — Opportunity discovery: Integrate reliable sources for internships, jobs, courses, and hackathons.

Phase 4 — Smart campus: Add interactive maps, verified facility information, and authorized service integrations.

Phase 5 — Student personalization: Add secure accounts, saved preferences, progress tracking, and appropriate notifications.

Phase 6 — Offline improvements: Add downloadable learning packs, saved resources, and synchronization when connectivity returns.

Each phase should be tested before its features are described as completed.

🌍 14. Expected Impact

CampusGo AI aims to improve the student experience in several ways.

📚 Better learning access: Students can ask questions and receive explanations through a convenient interface.

🧭 Clearer career planning: Students can explore skills and learning steps related to their interests.

🏆 Greater opportunity awareness: A future verified opportunity module can help students discover relevant internships and competitions.

📍 More convenient campus information: Campus services and facilities can be organized in one place.

📶 Improved offline accessibility: Selected local features can remain available during internet interruptions.

🔐 More privacy-conscious AI usage: Suitable tasks can be processed locally rather than automatically sending every prompt to a remote model.

🤝 Stronger collaboration: Future community features can support peer learning and team-based projects.

These are expected benefits, not yet measured outcomes. Actual impact should be evaluated through user feedback and testing.

🎯 15. Conclusion

CampusGo AI is designed to be more than a conventional AI chatbot. It aims to become a unified student companion that connects learning, skill development, career guidance, educational opportunities, and campus services.

By combining a locally hosted AI model with a lightweight web application and a modular backend, the project establishes a foundation for accessible, organized, and privacy-conscious student support.

The project begins with a practical prototype and can grow through carefully planned development, verified integrations, security checks, and real-world testing.

Our goal is to help students understand what to learn, identify what to do next, discover meaningful opportunities, and navigate their academic journey more effectively.

🚀 CampusGo AI — Your Campus. Your World. One App.

DEV Community: Dharshini Thirri

Campus Go AI

🚀

Your Campus. Your World. One App.

🌟 1. Project Overview

🎯 Our vision

💡 Why is this project important?

🛑 2. Problem Statement

🎯 3. Project Objectives

⚠️ 4. Existing System and Its Limitations

Common limitations

Why do we need CampusGo AI?

💙 5. Proposed Solution

📴 Offline mode

🌐 Online mode

⭐ 6. Important Features and Why They Matter

📚 Feature 1: AI Study Buddy

🧭 Feature 2: AI Career Guidance and Skill Roadmap

🏆 Feature 3: Jobs, Internships, and Hackathons

🧠 Feature 4: Learning Resources and Technology Updates

📍 Feature 5: Campus Discovery and GPS

🍱 Feature 6: Food and Transportation Services

🤝 Feature 7: Student Collaboration

🔔 Feature 8: Notifications and Reminders

🔐 Feature 9: Privacy-Conscious Local AI

🛠️ 7. Technology Stack and Its Importance

🧩 How the technologies work together

🏗️ 8. System Architecture

Layer 1: Frontend 🎨

Layer 2: Backend ⚙️

Layer 3: Local AI 🧠

Layer 4: Local Resources and Data 💾

Layer 5: Online Integrations 🌐

🔄 Complete request flow

👩‍💻 9. Complete Development Process

Step 1: Identify the problem 💡

Step 2: Define the solution and requirements 📝

Step 3: Set up the development environment 💻

Step 4: Organize the project files 📂

Step 5: Develop the backend ⚙️

Step 6: Develop the frontend 🎨

Step 7: Configure the local AI model 🤖

Step 8: Integrate AI with the backend 🔗

Step 9: Integrate the available features 🧩

Step 10: Run the application locally ▶️

Step 11: Test and debug 🐛

Step 12: Review privacy and security 🔐

Step 13: Use Git and GitHub 🌐

Step 14: Prepare the final demonstration 🎤

🧪 10. Testing and Validation

Functional testing

Integration testing

Offline testing

Security testing

🔐 11. Privacy, Security, and Responsible AI

✨ 12. Innovation and Uniqueness

🚀 What makes the idea valuable?

📌 13. Current Implementation and Future Development

🛣️ Future development roadmap

🌍 14. Expected Impact

🎯 15. Conclusion