Anthropic’s prompt suggestions are simple, but you can’t give an LLM an open-ended question like that and expect the results you want! You, the user, are likely subconsciously picky, and there are always functional requirements that the agent won’t magically apply because it cannot read minds and behaves as a literal genie. My approach to prompting is to write the potentially-very-large individual prompt in its own Markdown file (which can be tracked in git), then tag the agent with that prompt and tell it to implement that Markdown file. Once the work is completed and manually reviewed, I manually commit the work to git, with the message referencing the specific prompt file so I have good internal tracking.
Иран поразил нефтяной танкер под флагом США у берегов Кувейта14:49
，推荐阅读服务器推荐获取更多信息
ОАЭ задумались об атаке на Иран20:55
Подростки распылили перцовый баллончик на пассажиров электрички под Петербургом20:54
，更多细节参见电影
本周早些时候，AMD 宣布将向 Meta 出售价值高达 600 亿美元的 AI 芯片；本月稍早，Meta 亦与英伟达（Nvidia）达成了采购其当前及未来一代 AI 芯片的协议。
Захарова поинтересовалась возможностью посмотреть «Терминатора» в Молдавии14:59。PDF资料对此有专业解读