Five major category templates, allowing beginners to quickly build an evaluation system

LangSmith releases evaluator template library and reusable evaluators, simplifying multi-level evaluation work for AI agents. The templates cover five major categories: safety and protection, response quality, execution trace, user behavior analysis, and multimodal, including optimized evaluation prompts and rule-based evaluators, suitable for online monitoring and offline experiments. Reusable evaluators are centrally managed at the organizational level, with a new Evaluators tab, one-click deployment to new projects, and global updates to prompt words. Open-sourced and released with openevals v0.2.0, adding multimodal support.