请问HN：为人工智能应用实施日志记录和审计追踪的最佳方法是什么？
最近我在尝试一个小型的基于人工智能的项目，并开始考虑记录提示、响应和模型调用等内容。对于传统系统，监控工具可以处理大部分这些内容，但对于基于大语言模型（LLM）的应用，标准做法似乎不太明确，尤其是在需要适当的审计跟踪以便于调试或合规时。我很好奇团队们在生产环境中是如何处理这个问题的。人们主要是在构建自己的日志记录管道，还是有可靠的工具或平台可以帮助存储和审计LLM交互？
查看原文
so i’ve been experimenting with a small AI-based project recently and started thinking about logging around prompts, responses, and model calls etc etc.<p>for traditional systems observability tools handle most of this, but with LLM-based apps it feels less clear what the standard approach is, especially if you need proper audit trails for debugging or compliance.<p>curious how teams are handling this in production<p>are people mostly building their own logging pipelines, or are there reliable tools/platforms that help with storing and auditing LLM interactions?