👥

Team Size

2-5 Students

Collaborate, divide work, iterate together

🏃

Sprint Cadence

2 Weeks

4 sprints with demos at each checkpoint

🎯

Final Demo

5 Minutes

Pitch to VCs, entrepreneurs, and faculty

📊

Poster Session

36" × 48"

Network with industry leaders

Project Areas

🎨

Multimodal Apps

Sound, language, image, video processing and generation

📄

Data Extraction

Scraping, form filling, document processing

🤖

Assistants & Copilots

Domain-specific AI assistants and interns

Personalization

Content rewriting, adaptive experiences

💻

Coding & APIs

Code generation, testing, documentation

⚖️

Law & Medicine

Document processing in regulated industries

🏛️

Government & Policy

Public sector automation and analysis

🔊

Voice AI

Conversational interfaces and voice agents

🔍 Looking for Teammates?

Head to the #finding-teams channel in Slack to pitch your ideas and find collaborators who share your vision.

Open Slack

Project Proposal Format

01

Project Title

A memorable name for your project

02

Team Members & Emails

Names and Stanford email addresses

03

GitHub Alias

Link to repo and GitHub handles of all team members

04

1-Line Description

What your project does in one sentence

05

Overview

Problem statement, your solution, why existing solutions fall short, and how you address the gap

06

Timeline & Milestones

Week-by-week or sprint-by-sprint plan (we know these will change!)

Example

VisionaryAI

1-Line

A GPT-powered indoor navigation assistant that provides real-time conversational guidance to visually impaired users.

Overview

VisionaryAI combines real-time computer vision with LLMs to help visually impaired individuals navigate indoor environments. The system performs live object detection while a GPT-based dialogue layer generates spoken navigation instructions.

Gap Addressed

Existing solutions rely on static maps or rigid rule-based systems. VisionaryAI provides a conversational, vision-based assistant capable of reasoning over live camera input.

Academic Integrity & AI Tools

✅ Encouraged

AI Coding Assistants

Use of AI coding tools (GitHub Copilot, Claude, ChatGPT, Cursor, etc.) is actively encouraged. These tools represent the modern reality of software development.

  • Use AI to help write, debug, and understand code
  • Use AI to explore different implementation approaches
  • Use AI for boilerplate, documentation, and commit messages
📋 Required

What You Must Do

  • Document your use of AI tools in code comments when substantial code is AI-generated
  • Understand all code you submit (you'll be asked to explain it)
  • Properly attribute all external code, libraries, and resources
  • Obey license restrictions when using open-source code
🤝 Collaboration

Working Together

  • Within your team: Full collaboration expected
  • Between teams: Discussion of concepts and debugging allowed
  • Code sharing: Permitted with attribution to other teams
  • Open source: Permitted with proper attribution and license compliance
⚠️ Not Allowed

Honor Code Violations

  • Copying code from other teams without permission and acknowledgment
  • Submitting someone else's project as your own
  • Using AI to generate your entire project without understanding the architecture
  • Sharing guest lecture content outside the course without permission

🎬 See What's Possible

Watch last year's Demo Day to see the caliber of projects coming out of CS 224G.

Watch Demo Day 2025