LangChain把智能体测试、沙箱和评估整合到一起了，企业可以自己掌控从模型选择到部署的全流程，不用再拼凑各种工具。
LangChain宣布推出DeepAgents Harness，作为测试智能体行为的框架（harness）。同时提供LangSmith Sandboxes用于安全隔离的执行环境，以及面向LLM输出的评估（Eval）功能。这些组件集成主流模型提供商，并通过LangSmith Engine驱动“模型-测试-沙箱-评估”闭环。该方案旨在帮助企业基于自身领域知识和客户工作流，自主构建和优化智能体系统。
Harness: ✅ (DeepAgents) Sandboxes: ✅ (LangSmith Sandboxes) Eval: ✅ (LangSmith Sandboxes Model: integ...
Harness: ✅ (DeepAgents) Sandboxes: ✅ (LangSmith Sandboxes) Eval: ✅ (LangSmith Sandboxes Model: integrate with all the popular models and providers Plus we have the engine that helps you turn this flywheel: LangSmith Engine docs.langchain.com/langsmith/engi… own your agents! Aravind Srinivas @AravSrinivas Every enterprise will have its own model-harness-sandbox-eval flywheel with token value per watt optimization. This is the future. Simple reason: tacit knowledge about the domain and customers and their workflows that the company uniquely understands and has built trust around. 🔗 View Quoted Tweet 💬 4 🔄 0 ❤️ 6 👀 1159 📊 4 ⚡