LPU - Lovely Professional University
What you'll learn

This course provides a comprehensive introduction to Prompt Engineering and Agentic Artificial Intelligence (AI), focusing on the design, development, and deployment of intelligent AI systems using Large Language Models (LLMs). It covers fundamental to advanced prompting techniques, including zero-shot, few-shot, chain-of-thought, and structured prompting, enabling effective interaction with generative AI models. The course further explores Agentic AI systems, where AI agents can plan, reason, and execute tasks autonomously using tools and workflows. Students will gain hands-on experience in building real-world applications such as chatbots, automation systems, research assistants, and task planners using no-code/low-code platforms like n8n, along with integration of APIs and external tools. Emphasis is placed on practical learning, industry-relevant use cases, and developing skills required for emerging roles in AI automation, intelligent systems design, and generative AI applications. CO1 :: define the fundamentals of Prompt Engineering, Large Language Models (LLMs), and Agentic AI systems CO2 :: characterize different prompting techniques such as Zero-shot, Few-shot, Chain-of-Thought, Role-based prompting, and Tool-augmented prompts CO3 :: apply prompt design strategies to build real-world AI applications like chatbots, content generators, and automation agents CO4 :: analyze agentic workflows including planning, reasoning, memory, and tool usage CO5 :: investigate frameworks like LangChain, AutoGen, and n8n for building intelligent agents CO6 :: determine how to design, deploy, and optimize Agentic AI systems for real-world automation tasks


Avatar
Enjula Uchoi
Assistant Professor

Enjula Uchoi is a highly motivated researcher and emerging expert in Natural Language Processing (NLP), Low-Resource Language Technologies, and Generative Artificial Intelligence. His work is centered on addressing critical challenges in code-mixed and code-switched language processing, with a strong emphasis on English–Kokborok and other underrepresented languages. He has demonstrated strong expertise in designing and implementing machine learning and deep learning models, including LSTM, SVM, Hidden Markov Models, and Transformer-based architectures, for tasks such as language identification, sentiment analysis, and text generation. His research particularly focuses on computational efficiency, leveraging techniques like feature selection, pruning, and sequence optimization to enhance model performance in low-resource environments. Enjula has also explored cutting-edge domains such as Transformer-based language systems, reinforcement learning for text generation (GPT-based models), and Agentic AI, combining prompt engineering with intelligent automation. His work bridges the gap between theory and practice by developing real-world AI solutions, including AI-driven language learning tools, embedded systems for language preservation, and automation workflows using platforms like n8n. He is actively involved in scholarly research and has contributed to publications in areas such as quantum cryptography and NLP, while continuously expanding his expertise in next-generation AI systems, autonomous agents, and human-centric AI applications. With a strong vision of leveraging AI for social impact and linguistic inclusion, Enjula Uchoi is committed to advancing technologies that empower low-resource communities and preserve linguistic diversity through intelligent systems.