Claude Computer Use

Spec sheet

What it does

The computer use tool lets Claude use screenshots, mouse actions, and keyboard input to interact with a desktop environment.Read 4 Oct 2026 · platform.claude.com

Integrations

At launch, Anthropic said computer use was available through its API, Amazon Bedrock, and Google Cloud Vertex AI.Read 4 Oct 2026 · anthropic.com

Headquarters

Anthropic’s transparency hub identifies San Francisco, California, as its headquarters.Read 4 Oct 2026 · anthropic.com

Company

Anthropic describes itself as an AI safety and research company that builds reliable, interpretable, and steerable AI systems.Read 4 Oct 2026 · anthropic.com

Accuracy limits

Anthropic advises against using computer use for tasks requiring perfect precision or sensitive user information without human oversight.Read 4 Oct 2026 · platform.claude.com

Actions

The tool can request actions including screenshots, clicks, and typing, and can return short sequences of actions together.Read 4 Oct 2026 · platform.claude.com

Availability

The current computer toolset is available on the Claude API and Google Cloud; the page says it is not currently available in Claude Managed Agents.Read 4 Oct 2026 · platform.claude.com

Capabilities

The current computer toolset has 17 member tools, including screenshot, left_click, type, and zoom.Read 4 Oct 2026 · platform.claude.com

Data handling

Screenshots, mouse actions, keyboard inputs, and session files are stored in the developer's environment; Anthropic processes screenshots and action requests in real time as part of API calls.Read 4 Oct 2026 · platform.claude.com

Data retention

Anthropic says the client-side computer use tool is eligible for zero data retention, with API request retention governed by its API data retention terms.Read 4 Oct 2026 · platform.claude.com

Developer implementation

Developers add the computer use toolset to a Messages API request and run Claude’s requested actions in their own environment.Read 4 Oct 2026 · platform.claude.com

Environment

Anthropic’s reference environment uses a Linux desktop with a virtual X11 display and applications including Firefox and LibreOffice.Read 4 Oct 2026 · platform.claude.com

How it runs

Your application runs each computer action in an environment you control, returns the result to Claude, and repeats the process until the task is complete.Read 4 Oct 2026 · platform.claude.com

Isolation

The reference implementation runs the computer-use environment inside a Docker container for security and isolation.Read 4 Oct 2026 · platform.claude.com

Limitations

Anthropic describes computer use as imperfect and says scrolling, dragging, and zooming can be challenging.Read 4 Oct 2026 · anthropic.com

Maker identity

Anthropic describes itself as an AI safety and research company that builds reliable, interpretable, and steerable AI systems.Read 4 Oct 2026 · anthropic.com

Maker security certifications

Anthropic's Trust Center lists SOC 2 Type II, ISO 27001:2022, ISO/IEC 42001:2023, and HIPAA among its compliance resources.Read 4 Oct 2026 · trust.anthropic.com

Performance limits

Anthropic cautions that computer use can be slow, coordinate selection and tool choice can be unreliable, and performance may be lower in niche or multi-application workflows.Read 4 Oct 2026 · platform.claude.com

Pricing

Computer use follows standard tool-use pricing; requests incur model token costs, and screenshots are billed as image input.Read 4 Oct 2026 · platform.claude.com

Prompt injection protection

Classifiers scan tool results such as screenshots for potential prompt injections and can steer Claude to verify whether an instruction came from the user.Read 4 Oct 2026 · platform.claude.com

Prompt injection safeguards

Anthropic says classifiers scan tool returns for potential prompt injections and steer Claude to check whether suspicious instructions came from the user.Read 4 Oct 2026 · platform.claude.com

Safety advice

Anthropic recommends starting with low-risk tasks because computer use can be error-prone and may create risks such as spam, misinformation, or fraud.Read 4 Oct 2026 · anthropic.com

Security guidance

Anthropic recommends using a dedicated virtual machine or container with minimal privileges, restricting internet access, and requiring human confirmation for consequential actions.Read 4 Oct 2026 · platform.claude.com

Task loop

The application returns screenshots and other tool results to Claude so it can continue acting until it completes the task.Read 4 Oct 2026 · platform.claude.com

Use cases

Anthropic describes uses including automating repetitive processes, building and testing software, and conducting open-ended research.Read 4 Oct 2026 · anthropic.com

User consent

Anthropic instructs developers to inform end users of relevant risks and obtain their consent before enabling computer use in their products.Read 4 Oct 2026 · platform.claude.com

Where Specifiction places it

• AI Computer Use Agents#8 of 247.7