Browser Capabilities

Browser Capabilities

View as Markdown

This reference documents the browser runtime capability surface that sits on top of workspace.execute(...) and the runtime-aware SDK clients.

Use these pages alongside the API reference:

  • API reference explains resource endpoints such as workspaces, runtimes, operations, artifacts, and browser profiles.
  • Capability reference explains what browser methods and agent calls actually do.

Categories

  • Navigation - Page and context movement, loading, and page creation. (5 capabilities)
  • Interaction - Element targeting, typing, clicking, and readiness checks. (8 capabilities)
  • Extraction - Content retrieval, screenshots, evaluation, and read-side data access. (7 capabilities)
  • Events - Runtime-backed event listeners and event waiting patterns. (8 capabilities)
  • Agents - Natural-language and long-running browser agent capabilities. (6 capabilities)
  • Lifecycle - Runtime-level live, recording, and stop operations. (4 capabilities)