PlaceMate

A Personalized Placement Preparation Framework Using Assessment-Driven Learning and Generative AI

Comment

PlaceMate

Inspiration

Students preparing for placements often struggle to identify their weak subjects, decide what to study next, and follow a consistent preparation schedule. Generic study plans do not always account for individual strengths, weaknesses, or available study time.

We built PlaceMate to make placement preparation more personalized, structured, and accessible. Our goal is to help students understand their learning gaps and follow a clear path toward improvement.

What it does

PlaceMate is an AI-powered placement preparation platform that acts as a personalized learning companion.

  • Assessments: Evaluates students across multiple subjects to identify areas for improvement.
  • Personalized study plans: Generates day-wise learning plans based on weak subjects, selected topics, study duration, and daily study hours.
  • AI-generated notes: Provides learning material for individual topics.
  • Curated video resources: Recommends relevant YouTube videos to support conceptual understanding.
  • Topic-wise MCQs: Helps students practise and test their understanding.
  • Progress tracking: Monitors daily progress through an interactive dashboard.
  • Progressive learning: Unlocks subsequent learning content as students complete their daily tasks.
  • Continuous improvement: Allows students to retake assessments and generate updated study plans.

How we built it

PlaceMate uses a full-stack architecture combining a web frontend, a Python backend, Firebase services, and AI APIs.

  • Frontend: Next.js and Tailwind CSS for the user interface and interactive learning dashboard.
  • Backend: FastAPI and Python for application logic and API endpoints.
  • Database: Firebase Firestore for storing application data.
  • Authentication: Firebase Authentication with Google sign-in.
  • AI: Gemini and Grok for AI-powered learning workflows.
  • Video recommendations: YouTube Data API for finding relevant educational resources.

The workflow starts with a student assessment. The platform identifies weak subjects, lets the student select learning topics and available study time, and generates a personalized study plan. Students then work through notes, videos, and MCQ practice while tracking their progress.

Challenges we ran into

  • Personalization: Designing a workflow that turns assessment performance into a meaningful study plan rather than a generic schedule.
  • Study-plan generation: Structuring AI-generated learning plans around selected topics, preparation duration, and daily study hours.
  • Learning progression: Organizing daily tasks and unlocking subsequent content based on completion.
  • Content quality: Bringing together AI-generated notes, relevant video recommendations, and topic-wise practice questions in one learning experience.
  • Progress tracking: Connecting task completion with the dashboard so students can monitor their preparation.

Accomplishments that we're proud of

  • Built an end-to-end placement preparation platform with assessment-driven personalization.
  • Created a workflow that converts weak subject identification into a structured study plan.
  • Combined AI-generated notes, video resources, and MCQ practice in one platform.
  • Implemented progressive content unlocking to encourage consistent preparation.
  • Developed a dashboard for tracking learning progress and supporting reassessment.

What we learned

  • How to integrate frontend, backend, database, authentication, and AI services into one application.
  • How assessment results can guide personalized learning recommendations.
  • How to structure AI-generated content into actionable, day-wise learning tasks.
  • Why progress tracking and clear learning milestones matter in an educational application.
  • How to design a learning workflow that encourages students to practise consistently and evaluate their improvement.

What's next for PlaceMate

  • Introduce an interactive AI tutor that answers questions and explains difficult concepts step by step.
  • Improve recommendations using students' practice performance and learning history.
  • Add adaptive MCQs that adjust difficulty based on student performance.
  • Expand the range of placement preparation subjects and topics.
  • Introduce more detailed analytics to visualize improvement over time.
  • Integrate the BharatCode Model API into selected AI learning workflows to explore its capabilities for personalized tutoring and study-plan generation.

Built With

Share this project:

Updates

Submission history