CognifyQ in now Online!
We deployed CognifyQ, an LLM-based educational assessment platform built as part of my undergraduate thesis.
I am excited to share that CognifyQ is now deployed online.
CognifyQ is an LLM-based educational assessment platform developed as part of my undergraduate thesis in Department of Computer Science and Engineering at University of Dhaka. The project focuses on going beyond surface-level text matching to evaluate the semantic depth of student responses in a more meaningful and human-aligned way.
The platform was designed to support more practical and scalable assessment workflows, especially in educational settings where manual evaluation creates heavy workloads for teachers. It supports Bangla and English, handles multiple input formats, and is built to make automated assessment more accessible, consistent, and useful for both teachers and students.
As part of this work, we developed and deployed a full web-based system that brings together the research and engineering sides of the project. This included building the assessment workflow, integrating the language model pipeline, and making the platform available through a live public deployment.
Live Website
You can explore the deployed platform here:
Demo Video
A short demonstration of the system is available here:
Project Context
CognifyQ was developed as part of my undergraduate thesis, titled “Beyond Surface Metrics: Leveraging LLMs to Assess Semantic Depth of Human Responses.” The project reflects my broader interest in AI, natural language processing, educational technology, and human-aligned evaluation systems.
Deploying the platform online was an important milestone for me, because it turned the thesis from a research idea into a usable system that people can actually interact with. Research is nice, but seeing it survive contact with the real world is nicer.
