最新资讯
dev.to 用 Switch 构建 AI 投资委员会:多空研究员 Agent 协作 bloomberg.com 微软正结束向甲骨文租用 AI 云算力的协议 the-decoder.com Perplexity 推出常驻 AI Agent“Teammates” dev.to osFoundry的Loop和Graph是什么,何时该用哪个? dev.to 限制上下文而非限制评审:面向开源补丁的字节预算证据包 dev.to 约束自主智能体:用 GKE Agent Sandbox 实现亚秒级零信任执行 dev.to 实测:给 Claude Code 十个翻译工具,三次运行中有一次完全不用 unite.ai Ramp 数据:企业 AI token 用量增速超过支出增速 pub.towardsai.net AI 生成的 ICLR 评审对被拒论文更宽松:如何压力测试你的 rebuttal blogs.nvidia.com NVIDIA 开源工具如何助力研究者构建下一代 6G 网络 wired.com AI 公司正积极收购企业工作文件与邮件用于模型训练 wechat 网友用AI搓出来的“App”,可以直接在小红书玩起来了?
多元动态
登录 注册
智能体 x.com · @omarsar0

Eon 发布 Era:可重置的模拟企业环境,用于企业级 agent 评测与后训练

原文 我的收藏

一条 X 帖子转述 Eon 推出的 Era:它生成一个覆盖 Salesforce、Zendesk、Slack、Jira、Gong、Deel 及云数据库与存储的完整模拟企业,各系统模拟真实厂商行为,包括限流、分页和错误码,agent 通过实时 MCP 与 API 接口交互。由于环境由 Era 生成,它掌握精确的 ground truth,可重置公司并重跑相同任务,用于测试、基准评测、针对失败案例做后训练并衡量改动效果。转述称 Era 已上线且免费,并列出 NVIDIA、Decart、Composio 等研究合作方;上述说法来自二手转述与产品宣传,缺少独立验证。

AI推荐理由 转述 Eon 发布的 Era:生成覆盖 Salesforce、Zendesk、Slack、Jira 等系统的完整模拟企业,各系统模拟真实厂商行为(限流、分页、错误码),agent 通过 MCP 与 API 交互,可重置环境后重跑同一任务以对比模型或 prompt 改动。对 agent 评测与后训练有明确用途;但为二手转述加产品宣传,缺少独立验证与基准数据,'免费''已上线'等说法需以官方为准。

74 浏览 2,709 点赞 12 评论 3 转发 1

正文

Pay attention to this if you are building with agents. Simulated companies are a big deal for improving agentic products. This is because good agent evals need environments that behave like real companies. Era by Eon can generate a complete company across Salesforce, Zendesk, Slack, Jira, and other systems. Each system behaves like the real vendor, down to rate limits, pagination, and error codes. You can reset the company and rerun the same tasks after changing the model or the prompt. ![Ofir Ehrlich](https://pbs.twimg.com/profile_images/2084294815529791489/-2bwTP4a_normal.jpg) Ofir Ehrlich@OfirEhrlich You can’t safely test an enterprise agent on a real company’s data. So we built a company for it to work in. Era is live today, and it’s free. It generates a complete simulated enterprise that behaves like a real one across Salesforce, Slack, Jira, Zendesk, Gong, Deel and more, along with cloud databases and storage. Agents interact with it through live MCP and API interfaces. People leave. Deals change. Records get duplicated. Permissions differ across systems. And because Era generated the company, it knows the exact ground truth. Test, benchmark and improve agents against realistic enterprise workloads, use the failures for targeted post-training, then rerun the same environment to measure the impact. Huge thanks to our research partners [@NVIDIA](https://x.com/NVIDIA), [@Decart](https://x.com/Decart), [@Composio](https://x.com/Composio), [@openlayerco](https://x.com/openlayerco), [@Deel](https://x.com/Deel), [@Eragon](https://x.com/Eragon) and [@Plurai](https://x.com/Plurai), with more coming soon. [Your browser does not support the video tag.](https://video.twimg.com/amplify_video/2107124008479313920/vid/avc1/1920x1080/I56w2AHPIVmcFLFy.mp4?tag=29) [🔗 View on Twitter](https://x.com/OfirEhrlich/status/2107124107464905058/video/1) [🔗 View Quoted Tweet](https://x.com/OfirEhrlich/status/2107124107464905058)

来源报道 · 1 篇 · 以下链接均前往原始媒体

← 返回精选动态 原文

更多内容