Time Constraints: Despite the month-long hackathon, managing time effectively alongside academic commitments was a significant challenge, limiting the available time to work on the project until the final week.

LLM Setup: Ensuring that the platform remains cost-free for all users was a priority. This presented difficulties in fine-tuning a custom LLM or hosting a proprietary model, as these options can be resource-intensive and expensive. To overcome this challenge, the project utilizes the Llama3 LLM and employs complex architectures during inference to provide a high-quality, personalized tutoring experience without incurring additional costs.