Today, we’re thrilled to introduce Claude Cowork in Amazon Bedrock. You can now run Cowork and Claude Code Desktop on Amazon Bedrock, either directly or via an LLM gateway. From startups to large enterprises across all industries, organizations are using Claude Code in Amazon Bedrock to increase developer productivity and speed up delivery. With Amazon Bedrock, you can develop within your current AWS environment while preserving enterprise-grade security, ensuring regional data residency, and scaling inference seamlessly. Your data remains fully under your account’s control: Amazon Bedrock does not store prompts, files, tool inputs/outputs, or model responses, nor does it use them to train foundation models. With Claude Cowork in Amazon Bedrock, you can extend AI adoption across every knowledge worker in your organization through a desktop application capable of reading documents, performing multi-step research, processing files, and delivering completed work. In this post, we explore how Claude Cowork integrates with Amazon Bedrock and provide a practical example of how knowledge workers can use it. What is Claude Cowork? With Claude Cowork, users can easily assign research, document analysis, data processing, and report creation tasks to Claude directly from their desktop application. They gain access to the core Claude Desktop features, such as projects, artifacts, memory, file upload and export, remote connectors, skills, plugins, and MCP servers. Features requiring Anthropic-hosted inference—such as the Chat tab, Computer Use, and the Skills Marketplace—are not included, as Claude Cowork exclusively routes model inference through Amazon Bedrock in your AWS account. For a complete feature comparison with Claude Enterprise, refer to the Features page on 3P. Pricing follows a consumption-based model through your current AWS agreement and billing, with no seat-based licensing from Anthropic. How Claude Cowork Integrates with Amazon Bedrock.
Hacker News – Newest: „claude cowork“