Claude Code 与 Claude Cowork 正式面向政府机构开放

英文标题：Bringing Claude Code and Claude Cowork to government

Claude Code 与 Claude Cowork 现已在面向政府机构的 Claude for Government Desktop 中公开测试，运行于 FedRAMP High 授权环境。公共部门团队可以利用 Claude Code 构建和现代化软件系统，而 Claude Cowork 可直接与桌面文件协作，执行备忘录撰写、RFP 评审等工作。本次发布还加入了部门级计费与支出控制、分层管理配置、可防篡改的审计日志等治理功能，使机构更容易采购、授权和分配 AI 资源以完成使命。

打开原文相关 3.6 · 机会 1

中文

Claude Code 和 Claude Cowork 现已在面向政府机构的 Claude for Government Desktop 中进入公开测试阶段。该版本基于为商业客户提供的同一应用程序构建，并通过 FedRAMP High 授权环境交付。

借助 Claude Code，公共部门团队可以构建和现代化支撑公共服务的软件系统。Claude Cowork 可直接与桌面上的文件协作，让机构工作人员可以将备忘录撰写、RFP 评审、案件处理以及演示文稿制作等任务委派给 Claude。

此次扩展体验还带来了更多的治理能力。管理员可以设置配置默认值，并分配及控制各部门之间的支出。安全团队和授权官员可以获得防篡改的审计日志和相关文档，以支持机构的 ATO（授权运营）过程。

今天的发布使各机构能够更轻松地获取、授权并分配 AI 能力，以推进其使命。

新功能

Claude Code 与 Claude Cowork。 机构可获得与我们商业用户相同节奏的新能力。对话历史存储在机构管理的本地设备上。推理运行在 FedRAMP High 授权环境内部。

适配拨款周期的计费。 项目办公室可以通过标准席位将 AI 支出与拨款资金挂钩，也可以自定义席位层级并设置支出与模型使用上限，使用量以固定增量购买并设有“不得超过”的硬顶。管理员可以在管理控制台中按用户和按模型跟踪使用情况，并会在余额不足前收到自动消耗预警。

匹配部门组织结构的管理模式。 部门级管理员可以向子机构分配席位和预付使用额度，同时各子机构可自行管理其用户。管理员可以使用 SCIM 组映射来为特定席位层级设置速率限制、金额上限和允许使用的模型。此外，分层配置可为子机构设定默认值，包括 Claude 可以连接到哪些服务、哪些功能可用以及指导 Claude 如何与用户交互的指令。

设计上融入监督。 每项管理操作都会记录在哈希链式审计日志中，组织管理员可以直接在产品内审查。Anthropic 一侧的敏感操作需要双人审批。使用量导出仅包含计量数据，这样各机构可以在不移动敏感材料的情况下回应 ATO 和监察长（IG）的请求。

安全与监督

对于评估桌面部署的安全团队，我们公开提供 FedRAMP 安全配置指南，客户可据此以安全的方式配置其 Claude for Government 产品。

此外，FedRAMP 要求我们提供正式的变更通知，该通知包含与此变更相关的详细信息。

最后，新桌面客户端的渗透测试摘要也已提供，后续的渗透测试摘要将在可用时提供。变更通知和渗透测试摘要可通过 Anthropic 信任中心签署 NDA 后获取。该应用程序通过标准机构 MDM 平台进行部署。

入门指南

Claude for Government 从即日起开始提供测试版。Anthropic 仍是签约和计费方——机构无需单独的云提供商关系即可开始使用。

新客户可以在 claude.com/solutions/government 申请访问。

安全团队可以通过以下链接下载渗透测试产物。

English / 原文

Claude Code and Claude Cowork are now available in public beta in Claude for Government Desktop, built on the same application our commercial customers use and delivered through a FedRAMP High authorized environment.

With Claude Code, public sector teams can build and modernize the software systems that underpin public services. Claude Cowork works directly with files on the desktop, allowing agency staff to delegate memo creation, RFP reviews, casework, and decks to Claude.

The expanded experience also comes with additional governance capabilities. Administrators can set configuration defaults as well as allocate and control spending across departments. Security teams and authorizing officials get tamper-evident audit logs and documentation that supports the agency ATO process.

Today’s launch makes it easier for agencies to acquire, authorize, and allocate AI in pursuit of their missions.

What's new

Claude Code and Claude Cowork. Agencies get new capabilities on the same cadence as our commercial users. Conversation history is stored locally on the agency-managed device. Inference runs inside a FedRAMP High authorized environment.

Billing that fits appropriations. Program offices can tie AI spend to appropriated funds with standard seats or they can define their own seat tiers with spend and model limits, and usage is purchased in fixed increments with a hard not-to-exceed cap. Administrators can track usage per user and per model in the admin console, and automatic burndown alerts warn them before the balance runs low.

Administration that matches how departments are organized. Department-level administrators can allocate seats and prepaid usage to sub-agencies while allowing each to manage its own users. Administrators can use SCIM group mappings to set rate limits, dollar caps, and allowed models for specific seat tiers. Additionally, layered configuration sets defaults for sub-agencies including what Claude can connect to, which features are available, and instructions that guide how Claude interacts with users.

Oversight by design. Every administrative action is recorded in a hash-chained audit log that organization administrators can review directly in the product. Sensitive operations on Anthropic's side require two-person approval. Usage exports are metering data only so agencies can answer ATO and IG requests without moving sensitive material.

Security and oversight

For security teams evaluating the desktop deployment, we're publishing our FedRAMP Secure Configuration Guide as a public-facing document that customers can use to configure their Claude for Government product in a secure manner.

In addition, FedRAMP requires us to provide our formal change notification, which contains details associated with this change.

Lastly, a penetration-test summary is available for the new desktop client, and subsequent follow up penetration-tests summaries will be provided once available. The change notification and pentest summary are available under NDA through Anthropic’s trust center. The application deploys through standard agency MDM platforms.

Getting started

Claude for Government is available in beta starting today. Anthropic remains the contracted and billing party—agencies don't need a separate cloud-provider relationship to get started.

New customers can request access at claude.com/solutions/government.

Security teams can download the penetration-test artifact through the following link.