autograder-org / autoGrader-frontend

An automated assignment grading system that leverages LLMs and AI to enhance grading efficiency and reliability. It includes modules for data input, criteria definition, AI integration, consistency checks, and comprehensive reporting, aimed at improving educational outcomes.
https://autograder.dev
8 stars 5 forks source link

Design UI for First Phase of Auto Grader #7

Open parthasarathydNU opened 7 months ago

parthasarathydNU commented 7 months ago

Overview

We are developing the UI for the first phase of the AutoGrader project, a Next.js application leveraging ShadcnUI for component styling. Our goal is to design a visually appealing interface that incorporates a dark theme inspired by the aesthetics of these websites:

Objectives

This initial UI iteration will focus on simplicity and functionality, enabling users to interact with the application effectively through a chat interface. The primary features to include are:

  1. Assignment Creation:

    • Users can create new assignments via a chat interface.
  2. Rubric Creation:

    • Users can develop rubrics interactively through the chat interface.
  3. Workspace:

    • A dedicated area where users can organize and access their previous chats, assignments, and rubrics.
  4. Persona Tab:

    • A feature allowing users to browse through various "personas," complete with detailed descriptions of each persona’s expertise, grading style, animated profile pictures, and voice clips. This facilitates persona-based assignment and rubric generation, as well as grading processes.

Upcoming Features

The following functionalities are planned for future updates:

  1. Conversation Continuation:

    • Ability to retrieve and continue previous conversations.
  2. Persona Management:

    • Options for users to browse existing personas or create new ones based on their preferences.
  3. Persona Integration:

    • Integration of personas into the creation and editing processes for assignments and rubrics.
  4. User Profile Customization:

    • Enhanced user profiles that allow for deeper personalization, including voice settings and previews of work generated by selected personas.

Design Considerations

Feedback and Iteration