Foundations of LLMs and Generative AI

Explain what a large language model is and how next-token prediction underlies its behavior

Describe tokens, context windows, and how token limits affect prompt and response design

Compare base models, instruction-tuned models, and chat models and when to use each

Explain temperature, top-p, top-k, and max tokens and their effect on output

Describe what embeddings are and how vector similarity enables semantic search

Identify common LLM failure modes: hallucinations, prompt injection, and stale knowledge

Compare Gemini, OpenAI, and Anthropic models on criteria relevant to agent development (tool calling support, context size, latency, cost)

Define what an AI agent is and how it differs from a plain chatbot