LLM Notes

The former LLM page mixed several layers. Follow this sequence instead:

• AI fundamentals — tokens, transformers, inference, and decoding.
• AI Prompt Engineering — zero-shot, few-shot, chain-of-thought, negative prompting, and templates.
• AI models and providers — model capabilities, workload selection, provider access, hosting, and portability.
• Knowledge bases — retrieval-augmented generation.
• Agents — tools, orchestration, state, and autonomy.
• Infrastructure and evaluation — production controls, observability, evaluation, and release gates.
• AWS AI Services — AWS implementations of the preceding architecture.

Use this page as the stable link for older references. It intentionally contains no second copy of those explanations.