Recent discussions in the field of artificial intelligence have highlighted the evolving landscape of prompt engineering. Notably, the introduction of DSPy has been recognized as a significant advancement in the large language model (LLM) space, with proponents claiming it represents a new paradigm for prompting. Structured prompting has also emerged as a critical requirement for developing real-world LLM applications, although concerns regarding its impact on performance and reasoning capabilities have been raised. A comprehensive report analyzing over 200 prompting techniques and more than 1,500 prompting papers has been released, with real companies utilizing it to evaluate potential hires. Additionally, a 76-page survey paper has been published, detailing a structured understanding and taxonomy of 58 text-only prompting techniques and 40 techniques for other modalities, focusing on discrete prefix prompts rather than cloze prompts. This ongoing dialogue underscores the sensitivity of LLMs to prompt variations and the necessity for intent-based prompt calibration to enhance performance consistency across tasks.