Taklif.AI: LLM-Powered Platform for Interest-Based Personalized College Assignments

2026-05-07

AI Summary

Traditional one-size-fits-all assignments often fail to accommodate students’ diverse interests and cognitive profiles, leading to low engagement and increased academic dishonesty. This work proposes a novel large language model–driven approach to personalized assignment generation that, for the first time, integrates students’ extracurricular interests and cultural backgrounds into task design, moving beyond paradigms reliant solely on academic performance. The method employs structured prompt engineering alongside dual quality assurance mechanisms on both input and output to ensure relevance and rigor. Implemented as a Next.js application on an AWS serverless architecture, the system leverages the Llama 3.3 70B model via LiteLLM for multi-provider load balancing and utilizes LangChain for prompt orchestration. In an initial evaluation with 68 users (65 students and 3 instructors), 84% reported that the personalization feature provided meaningful educational value.

Abstract

Educators face significant challenges in creating engaging, personalized assignments that accommodate students' diverse interests and cognitive abilities. Traditional one-size-fits-all assignments frequently lead to decreased student engagement and increased reliance on unethical practices such as plagiarism. To address these challenges, we present Taklif.AI, a platform that leverages Large Language Models (LLMs) to automatically generate personalized assignments tailored to individual student interests. Unlike existing AI-powered educational platforms that personalize based on academic performance metrics alone, Taklif.AI incorporates students' extracurricular interests and cultural contexts into the assignment generation process through a structured prompt engineering pipeline with input and output guardrails. The platform employs a serverless architecture on AWS with Next.js, using Llama 3.3 70B as the primary LLM via LiteLLM for multi-provider load balancing and LangChain for prompt orchestration. We describe the system architecture, the prompt design methodology, and the guardrails framework that ensures output quality. Preliminary user acceptance testing with 68 participants (65 students and 3 educators) indicates positive reception, with 84% of participants rating the personalization feature as beneficial. We discuss the platform's current capabilities and limitations, and outline directions for rigorous empirical evaluation of learning outcomes.

Problem

• personalized assignments
• student engagement
• plagiarism
• interest-based learning
• educational personalization

Innovation

• personalized assignments
• Large Language Models (LLMs)
• prompt engineering
• interest-based personalization
• guardrails framework