Which One Is Right?

Three cards on the table, each needing an architecture decision: RAG, long context, fine-tuning, or no LLM at all. (1) An insurance knowledge bot: 4,000 policy documents, edited weekly, and every answer must point at its source because a regulator reviews them. (2) A marketing copy generator: the knowledge required is trivial, but the tone must land in the brand's exact voice every time, and you have 3,000 past pieces written in that voice. (3) An FAQ page: 40 fixed question-answer pairs unchanged for a year, 200 queries a day.

Success: A defensible choice per card, with the trade-off you accepted named out loud.