While developing Engibot, several challenges emerged. One of the primary obstacles was data acquisition; securing a detailed dataset containing frequently asked questions and their respective answers about engineering colleges proved elusive. To address this, we initiated outreach to multiple colleges and spearheaded surveys among students and parents. This endeavor resulted in a proprietary dataset tailor-made for our training needs. Another significant challenge stemmed from the diverse ways users formulated their questions, introducing ambiguities. By harnessing the power of the NLTK library, we enhanced Engibot's natural language processing skills, equipping it to decipher and manage an expansive array of user queries.