From developer desks to the entire organization: Running Claude Cowork at Amazon Bedrock
Today, we are excited to announce Claude Cowork at Amazon Bedrock. You can now use Cowork and Claude Code Desktop through Amazon Bedrock, directly or through the LLM gateway.
From startups to global enterprises across every industry, organizations build with Claude Code at Amazon Bedrock to improve developer productivity and accelerate delivery. With Amazon Bedrock you can build within your existing AWS environment, maintain enterprise security and regional data residency, and scale. Your data remains under the control of your account: Amazon Bedrock does not store data, files, tool inputs and outputs, or model responses, and does not use them to train underlying models.
With Claude Cowork at Amazon Bedrock, you can extend AI adoption to all knowledge workers in your organization, with a desktop application that reads documents, runs multi-step research, processes files, and returns completed work.
In this post, we walk through how Claude Cowork integrated with Amazon Bedrock and show an example of how knowledge workers use it in practice.
What is Claude Cowork
With Claude Cowork, your users can submit research, document analysis, data processing, and report production to Claude from the desktop application. They get basic Claude Desktop capabilities including projects, artifacts, memory, file upload and export, remote connectors, capabilities, plugins, and MCP servers. Features that require consideration handled by Anthropic, including the Conversation tab, Computer Usage, and Skills Marketplace, are not included because the Claude Cowork routing model is exclusive to Amazon Bedrock in your AWS account. For a full feature comparison with Claude Enterprise, see Features on 3P.
Pricing is based on usage using your existing AWS agreement and billing, excluding seat licensing from Anthropic.
How Claude Cowork met Amazon Bedrock
Amazon Bedrock serves as an inference backend for your AWS account and supported AWS regions.
Fixing Claude Cowork in Amazon Bedrock takes two steps. First, users download the Claude Desktop application to their device. Second, your device management system (such as Jamf, Microsoft Intune, or Group Policy) pushes a configuration to Claude Desktop that activates inference mode, specifying the model ID and Amazon Bedrock Inference Profile, authentication method, and organizational policies. If your organization centralizes access to the model through the LLM gateway, you point the Claude Desktop to the gateway URL using the same managed configuration.
If your organization is already building with Claude Code on Amazon Bedrock, Claude Cowork can use the same setup.
Figure 1: The following diagram shows the end-to-end flow
The app has three exit modes, all of which are under your control. Model specification to Amazon Bedrock in AWS Regions that you configure. MCP server connections, if configured, go to the endpoints you authorize. Anthropic only receives aggregated telemetry (token counts, model ID, error codes, unknown device identifier), which can be turned off through configuration options.
Amazon Bedrock offers In-Region, geo cross-Region, and cross-Region profiles so you can choose the right level of occupancy data for your organization.
Claude Cowork works with AWS services you already use:
For information on MDM configuration, credentials, MCP servers, and plugins, see the Claude Cowork Configuration Reference.
Claude Cowork in action
With the configured integration, your users open Claude Desktop and start delegating work. Claude Cowork can connect to external data sources through MCP servers, giving Claude access to live documents, web searches, and other tools as applicable.
For example, a product manager is planning a new notification feature for a university athletics application hosted on AWS. They have client meeting notes that point to different approaches, a set of project requirements, and an estimated time to reconcile them. They upload them to Cowork.
Claude compares different inputs and combines them into one product. It examines the proposed method, research alternatives, flags technical challenges, and supports recommendations with evidence points. Connected to the AWS Documentation MCP server and the MCP web search server, Claude briefly supports current service documentation, market context, and competitor positioning.
Figure 2: Product manager converting meeting notes into a product brief with Claude Cowork
In minutes, the product manager has a structured brief based on current sources and ready for review. The same pattern applies to other knowledge workers. The operations manager can consolidate the scattered documents into an SOP. A financial analyst can turn raw data into a formatted monthly update. A research team can combine findings from multiple sources into a single report.
The conclusion
With Claude Cowork at Amazon Bedrock, you can extend AI adoption to all knowledge workers in your organization while keeping your data in your AWS environment. Claude Cowork is available on macOS and Windows in the AWS Regions where Claude's models are available on Amazon Bedrock. To get started, download Claude Desktop from claude.com/download and see the Claude Cowork Setup Guide.
Try Claude Cowork today and submit a response to AWS re:Submit Amazon Bedrock or through the usual AWS support contacts.
About the writers
