跳到正文
Rohan Paul· @rohanpaul_ai · X·· 4 小时前AI 评分66
AI 导读

Eon 发布 Era,通过描述一家公司来生成完整模拟企业,并把数据写入 Salesforce、Zendesk、Jira、Slack 和 Gong,智能体通过兼容厂商的 MCP 与 REST 接口与之交互。由于所有记录由 Era 生成,系统可用代码而非语言模型计算每个问题的确切答案,评测无需人工或模型裁判。开发者可重置公司、更换模型或提示词并重跑相同任务,以衡量此前失败样本上的后训练是否有效。

正文

Enterprise agents usually get tested against mocks, narrow synthetic datasets or production, and each of those hides something different.

Era by Eon tries a 4th option: you describe a company, and it generates one and writes it into Salesforce, Zendesk, Jira, Slack and Gong behind vendor-compatible MCP and REST interfaces.

Because Era wrote every record, code computes each question's exact answer without a language model, so grading needs no human or model judge.

Developers can then reset the company, swap a model or prompt, and rerun identical tasks to measure whether post-training on earlier failures helped.

引用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, @Decart, @Composio, @openlayerco, @Deel, @Eragon and @Plurai, with more coming soon.
在 X 查看被引用的帖子

来源:Rohan Paul · x.com