333

Chinese Composition Assessment

About

This solution analyses photos of handwritten Chinese compositions to provide scores and feedback based on teacher-configurable rubrics. The technical core combines Optical Character Recognition (OCR) with LLMs for text extraction. A multi-agent system separates perception from analysis, utilising LLMs to evaluate content against JSON-configured rubrics and employing semantic analysis LLMs to generate comprehensive feedback summaries.

Features

Handwriting Analysis: Capable of processing and scoring photos of handwritten Chinese text.
Configurable Rubrics: Allows teachers to set specific scoring criteria and rubrics.
Detailed Feedback: Generates scores along with natural language summaries and suggestions.

Video

← STEM Project via Robot Dog with Agentic AI Assessment: Cloze Test Generation →

Latest Exemplars & Use Cases

Assessment: Cloze Test Generation

Assessment: Cloze Test Generation

Agents, Evaluation, LTTC

This system utilises multi-agent collaboration to automatically source and check content from the web and generate cloze (fill-in-the-blank) tests, publishing them with learning management systems (LMS). It employs a multi-agent workflow in which one agent handles...

STEM Project via Robot Dog with Agentic AI

STEM Project via Robot Dog with Agentic AI

Agents, LTTC, Teaching Assistant

This initiative integrates Agentic AI with a quadruped robot dog to create a hands-on STEM learning experience, allowing students to apply abstract concepts in a physical environment. The solution integrates Agentic AI for autonomous decision-making using LLM-based...

Smart Student Handbook

Smart Student Handbook

Agents, Instructional Planning, LTTC, Teaching Assistant

This agent addresses information overload by transforming the student handbook into an interactive dialogue interface. Instead of manually searching through dense documents, students can access essential information and receive clear, conversational explanations of...