做智能体评估的可以看看,LinkedIn分享怎么把追踪数据变成黄金数据集,还教你怎么训LLM当裁判。
LinkedIn的Tanvi Motwani将参加LangChain在纽约举办的Interrupt NYC活动,分享Agentic Eval Playbook。该手册涵盖将智能体追踪转化为黄金数据集、训练LLM-as-a-Judge系统,以及为生产环境智能体构建离线与在线监控。活动定于9月24日举行。
.@LinkedIn is joining us at Interrupt NYC. Tanvi Motwani will share the Agentic Eval Playbook behin...
. @LinkedIn is joining us at Interrupt NYC. Tanvi Motwani will share the Agentic Eval Playbook behind LinkedIn's Hiring Assistant: turning agent traces into golden datasets, training LLM-as-a-Judge systems, and building offline/online monitoring for production agents. Catch her talk + more @ Interrupt NYC, Sept 24. interrupt.langchain.com/nyc 💬 1 🔄 0 ❤️ 4 👀 1973 📊 1 ⚡