ProductsMulti-source

CoreWeave 发布 Forge:打通智能体生产环境的评测与调试闭环

Why we picked it

CoreWeave 把追踪失败、生成评测集、验证修复这三步做进了一个平台,不用再自己拼工具链。比起 LangSmith 这类独立评测产品,它背靠自家 GPU 云,算力也一起给。做智能体上线运维的团队可以看看。

CoreWeave 推出 CoreWeave Forge,定位是让 AI 智能体在上线后保持可靠的一体化工具平台,由员工 AbhijayArora 在视频中讲解。产品核心思路是:智能体跑通一次并不够,需要在生产环境中持续运行完整闭环——追踪真实失败案例、把失败转化为评测集(evals)、再验证修复是否有效后才能发布。

Body

Forge 针对的痛点是大多数团队缺乏统一工具链,需要自己拼装追踪、评测、验证等多个环节的组件,导致维护成本高、迭代节奏变慢。Forge 把整个循环整合在同一个平台内,减少胶水代码。

这与 LangSmith、Braintrust 等智能体评测产品处于同一赛道,CoreWeave 的差异化在于其本身提供 GPU 云基础设施,可以把算力、追踪、评测打包给企业客户。做智能体工程化的开发者和企业运维团队是主要受众。

Original · CoreWeave

Getting an AI agent working once is not the goal. Keeping it reliable in production means running the whole AI loop: tracing real failures, turning them into evals, and proving a fix actually works before you ship.

Most teams lose momentum gluing all of the tools together. We built CoreWeave Forge to keep the entire loop working together.

@AbhijayArora explains CoreWeave Forge in the video below.

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include CoreWeave Forge, agents, benchmarks.

Source attribution: curated from CoreWeave (@CoreWeave). Cross-source corroboration: 3 independent sources have covered this development (including Vercel AI, Lenny Rachitsky), confirming industry-wide signal strength.