Generative AI and LLMs – Basic Applications

This exam validates your ability to use Large Language Models (LLMs) and Generative AI in Python. The focus is on basic usage, prompt engineering, and integrating models via APIs.

You will be tested on topics such as:

• Basic LLM concepts and the difference between training and inference
• Tokens, model sizes, and output control
• Prompt engineering: system, user, and assistant prompts
• Prompt strategies: few-shot, chain-of-thought, and output formatting
• Using APIs such as OpenAI, Azure, and Hugging Face
• Integrating LLMs into Python solutions (e.g., a chatbot, writing assistant, or coding assistant)
• Error handling, secure access, and timeout strategies
• Ethical considerations: bias, hallucinations, and responsible use of AI