Agentic AI: Prompt Engineering and LLM Essentials

Learn how Large Language Models and prompting power modern AI agents

Before building effective agents, you must first understand the engine that powers them.

In this three-week course, you’ll learn how Large Language Models (LLMs) work and how to design prompts that transform them from simple text generators into reliable, agentic systems capable of reasoning, planning, and tool use.

You’ll gain hands-on experience building working AI systems in Python, learning the core principles behind prompt engineering, structured outputs, and agent design patterns.

Understand prompt engineering and LLM reasoning

LLMs are powerful but unpredictable without proper design. On this course, you’ll explore how they reason, where they fail, and how issues such as hallucination, token limits, and context window constraints impact performance.

You’ll develop practical prompt engineering skills using techniques such as chain-of-thought prompting, self-ask prompting, and few-shot learning. These methods help guide models toward more accurate and structured reasoning, forming the basis of effective AI prompt engineering.

Learn context engineering and structured outputs

Next, you’ll learn context engineering principles and how to structure information so that LLMs can reason effectively and consistently.

Build AI agents using core design patterns

Finally, you’ll implement three core agentic design patterns in code: ReAct, Reflection, and Plan and Execute.

You’ll compare how each pattern performs on the same problems and learn when to apply each approach in practice. By combining these methods, you’ll build more capable AI agents that can plan, reason, and adapt.

This course is for technology enthusiasts, software developers, data professionals, product managers, and business leaders who want to understand agentic AI.

No prior AI engineering experience is required, though basic familiarity with concepts like APIs and Large Language Models will be helpful. It is ideal for professionals exploring career transitions into AI engineering, team leads evaluating agentic AI for business applications, and curious learners who want to move beyond chatbots and understand autonomous AI systems.

Learners need a computer (Windows, macOS, or Linux) with at least 8 GB RAM and a stable internet connection. Python 3.10 or later should be installed, along with a code editor such as VS Code. No paid software or specialised hardware is required.

This course is for technology enthusiasts, software developers, data professionals, product managers, and business leaders who want to understand agentic AI.

No prior AI engineering experience is required, though basic familiarity with concepts like APIs and Large Language Models will be helpful. It is ideal for professionals exploring career transitions into AI engineering, team leads evaluating agentic AI for business applications, and curious learners who want to move beyond chatbots and understand autonomous AI systems.

• Explain how generative AI, foundation models, and large language models support language-based AI applications.
• Apply prompt engineering techniques, including zero-shot, one-shot, few-shot, self-ask, and structured prompting, to improve LLM responses.
• Develop python-based agent workflows using core design patterns such as ReAct, Reflection, and Plan-and-Execute.
• Evaluate agent outputs using validation checks, retry logic, structured planning, and human review before execution.
• Investigate how context engineering, context windows, token limits, conversation history, and tool observations affect agentic AI workflows.