Adaptive AI Study Strategist (AAISS)

[rahulydv39]

Track

Reasoning Agents (Azure AI Foundry)

Project Name

Study Agent AI: Adaptive Learning Strategist

GitHub Username

rahulydv39

Repository URL

https://github.com/rahulydv39/adaptive-ai-study-strategist

Project Description

Traditional study platforms offer static roadmaps. We built a dynamic, multi-agent pipeline using Azure AI to create a truly adaptive learning experience.

The Assessment Agent: Dynamically generates a custom 10-question quiz based on the user's chosen topic to gauge their current skill level.

The Planner Agent: Analyzes the quiz results and generates a highly structured, personalized study syllabus.

The Engagement Agent: Operates asynchronously to draft and automatically send a welcome email and study commitment reminder directly to the user's inbox via SMTP.

Demo Video or Screenshots

Demo Video : https://youtu.be/ZBBDrpgXako
Screenshots :

Primary Programming Language

Python

Key Technologies Used

Frontend: React (Vite) for a fast, responsive, and dynamic user interface.

Backend: Python and FastAPI to orchestrate the multi-agent pipeline.

AI & LLMs: Azure AI Projects and Reasoning Agents to handle the heavy lifting of contextual generation.

Integrations: Standard Python smtplib for automated, background email dispatching.

Submission Type

Individual

Team Members

No response

Submission Requirements

• My project meets the track-specific challenge requirements
• My repository includes a comprehensive README.md with setup instructions
• My code does not contain hardcoded API keys or secrets
• I have included demo materials (video or screenshots)
• My project is my own work with proper attribution for any third-party code
• I agree to the Code of Conduct
• I have read and agree to the Disclaimer
• My submission does NOT contain any confidential, proprietary, or sensitive information
• I confirm I have the rights to submit this content and grant the necessary licenses

Quick Setup Summary

1. Clone the repository and navigate to the project folder.
2. Configure Environment: Create a .env file in the root directory and add your Azure AI Project credentials and SMTP details (for the email agent).
3. Start the Backend: - Navigate to the 2-reasoning-agents directory.
   • Run python -m venv venv and source venv/bin/activate to start the virtual environment.
   • Run pip install fastapi uvicorn python-dotenv azure-identity azure-ai-projects pydantic
   • Start the FastAPI server: uvicorn server:app --reload
4. Start the Frontend:
   • Open a new terminal tab and navigate to the frontend folder.
   • Run npm install followed by npm run dev.
   • Open localhost:5173 in your browser.

Technical Highlights

• Multi-Agent Orchestration: Successfully chained distinct Azure AI Reasoning Agents (Assessment, Planner, and Engagement) to autonomously pass data between each other based on user input.
• Asynchronous UI/UX Architecture: Engineered a decoupled React state management flow that safely handles long-running background tasks (like the SMTP email dispatch) without freezing the user interface.
• Graceful Fallback Protocols: Implemented strict error handling and graceful fallbacks in the Python FastAPI layer to ensure the API always returns a stable state to the frontend, even if third-party SMTP servers time out.
• Dynamic Assessment Loop: Built a real-time, state-driven dynamic quiz component that instantly informs the generation of the final study syllabus.

Challenges & Learnings

Orchestrating multiple AI agents to run sequentially without freezing the user interface was our biggest hurdle. We had to heavily optimize our React state management to decouple the UI rendering from the long-running background tasks (like the SMTP email dispatch). We eventually engineered a custom asynchronous flow that reveals the study plan instantly while the email agent finishes its work in the background.

Contact Information

rahulyadav969102@gmail.com

Country/Region

India

[rahulydv39]

AAISS