Generative Artificial Intelligence (AI) has been transforming personal and professional domains by enabling creative content generation and interactive problem-solving. However, the influence of users' grammatical abilities on the responses generated by these technologies remains unclear. This exploratory study investigated how language and grammar abilities, particularly in Spanish, affected the quality of responses provided by ChatGPT (free version). While Long Language Models (LLMs) perform well in various tasks, challenges arise with grammatical moods specific to non-English languages, such as the subjunctive in Spanish. Higher education students were chosen due to their familiarity with AI and its potential use in learning. The research assessed ChatGPT's ability to process instructions in Chilean Spanish, focusing on how linguistic complexity, grammatical variations, and informal language impacted output quality. The findings indicate that varied verbal moods and complex sentence structures significantly affect prompt evaluation, response quality, and the length of the responses. Based on these results, a framework is proposed to guide higher education communities in promoting digital literacy among teachers and students and in integrating AI into teaching and learning processes.