# AI-Powered Automated Assessment and Feedback Agent

---

## 🏆 Hackathon Info

This project was developed for the [Microsoft Hack Together: AI Agents Hackathon](https://microsoft.github.io/AI_Agents_Hackathon/rules/) (April 8–30, 2025).

- See the [Official Rules](https://microsoft.github.io/AI_Agents_Hackathon/rules/)
- Status: Hackathon prototype/MVP

---


> An intelligent, automated system designed to significantly reduce teachers' workload by providing instant assessment and personalized feedback for student assignments.

---

## 🎯 Key Features

- **Automated Grading:** Instantly grades student submissions across various assignment types, including short answers, essays, and quizzes.
- **Personalized Feedback:** Provides detailed, actionable feedback tailored to each student's individual performance and learning needs.
- **Resource Recommendations:** Suggests targeted educational resources based on identified strengths and weaknesses to support ongoing learning.

---

## ⚙️ How It Works

1. **Teacher uploads student submissions** through an easy-to-use interface.
2. **AI analysis powered by Azure OpenAI and Cognitive Services** quickly assesses student work.
3. **Detailed, individualized feedback** is generated immediately, enabling teachers to efficiently review and share results with students.

---

## 🚀 Technical Stack

- **TypeScript:** Ensures reliability, maintainability, and scalability.
- **Azure OpenAI:** Provides advanced NLP capabilities for nuanced and accurate assessment.
- **Azure Cognitive Services:** Enhances semantic analysis for precise feedback generation.

---

## 📖 Educational Impact

- Reduces hours spent grading and marking.
- Improves quality and consistency of student feedback.
- Allows teachers more time to focus on direct student interaction and lesson planning.

---

## 🔮 Future Enhancements

- Integration with major Learning Management Systems (LMS) for streamlined workflow.
- Expansion of supported assignment types and subjects.
- Development of analytics dashboards for deeper insights into class performance.

---

## 📽️ Demonstration Video

[Coming soon: View a full demonstration of the agent in action.]

---

## 👥 Team
- **Josh Creek**  
  [jcreek.co.uk](https://jcreek.co.uk)

---

## 🛠️ Getting Started

This project uses [SvelteKit](https://kit.svelte.dev/) and [TypeScript](https://www.typescriptlang.org/) with [pnpm](https://pnpm.io/) as the package manager.

### Prerequisites
- [Node.js](https://nodejs.org/) (v18 or newer recommended)
- [pnpm](https://pnpm.io/installation)

### Installation & Running Locally
```bash
pnpm install
pnpm dev
```
The app will be available at `http://localhost:5173` (or the port shown in your terminal).

---

## 📚 Resources
- [Hack Together: AI Agents Hackathon – Introduction & Getting Started](https://www.youtube.com/watch?v=RNphlRKvmJQ)
- [Hack Together: AI Agents Hackathon – Building Your Agent](https://www.youtube.com/watch?v=Aq30zfbWNSQ)

---

## 📌 License
Licensed under the Business Source License 1.1.  
See LICENSE file for details.