Campus Copilot — AI Academic Assistant for a College Student

Description and use

Campus Copilot aggregates student academic data, applies deterministic logic, and augments with Gemma 3 4B AI recommendations, while remaining functional without GPU via graceful fallbacks.

Problem

College students have fragmented academic information across attendance, assignments, exams, notes, and to‑do lists, making it hard to prioritize actions.

Outcome

Campus Copilot unifies academic data, applies deterministic calculations, and augments with AI‑generated recommendations, enabling students to focus on high‑risk tasks and study efficiently, even without GPU resources.

Workflow

• 1. User logs in via JWT and bcrypt authentication.
• 2. Backend retrieves student context from SQLite (attendance, assignments, exams, notes, tasks).
• 3. Deterministic logic calculates attendance risk, deadline urgency, and task priority.
• 4. Frontend displays dashboard with attendance ring, warnings, deadlines, and recommended actions.
• 5. User interacts with contextual chat; assistant calls backend AI service to generate actions (e.g., create_task, start_study_block).
• 6. AI service uses prompt templates and Gemma 3 4B via Ollama; if Ollama offline, rule‑based fallback is used.
• 7. Assistant returns structured actions and natural language responses to the frontend.
• 8. User executes actions; backend updates SQLite and re‑evaluates priorities.

Evidence

College students often have information scattered across attendance, assignments, exams, notes, and to‑do lists.

Source

It combines deterministic academic logic with an open-weight AI workflow to turn campus context into concrete actions.

Source

All AI features have graceful rule-based fallbacks when Ollama is unavailable, so the core application remains functional without a GPU.

Source

Campus Copilot uses Gemma 3 4B, Google's open-weight model, as its primary AI model during local development.

Source