Capabilities Guide

Captain Who capabilities are organized in several layers. Distinguishing them helps avoid treating “documented,” “connected,” and “authorized to run” as the same thing.

CapabilityPlain-language meaningWhat you primarily do
ToolThe agent's hands and eyesDefine the goal; inspect tool activity and approvals
SkillTask instructions and supporting resourcesSelect, install, enable, or update a skill
MCPA general-purpose connection to external toolsConfigure a local server and authorize its launch and calls
Multi-AgentA collaborative group managed by a root agentDefine the division of work, observe subagents, and handle approvals
Scheduled AutomationStarts a root-agent task on a scheduleSet the schedule, goal, permissions, and notifications
Browser AutomationAn agent controls managed web pagesEnable the capability, prepare a page, and approve sensitive actions
Office and ArtifactsWork with documents, spreadsheets, presentations, PDFs, and imagesChoose a skill, provide inputs, and verify the output

How capabilities work together

A task may use several capability layers. For example, “Summarize industry developments and update a spreadsheet every week” could work as follows:

  1. A scheduled automation starts a root agent weekly.
  2. The agent uses a web tool to research sources.
  3. It activates the Spreadsheets Skill and updates the workbook according to that workflow.
  4. It delegates research to multiple subagents if appropriate.
  5. File writes remain subject to the scheduled automation's frozen permissions and approval rules.

These layers do not automatically authorize one another. Installing a skill does not enable MCP. Allowing automatic calls to an MCP server does not expand file permissions. A scheduled automation also does not bypass ordinary agent approvals or safety checks.

If you are unsure which capability to choose

  • For a fixed built-in action, start with Tools.
  • For a particular method, template, or Office workflow, use a Skill.
  • To connect a third-party local tool, use MCP.
  • When independent subtasks can run in parallel, use Multi-Agent.
  • When the same task should repeat on a schedule, use a Scheduled Automation.

For a more detailed comparison, see Choosing the Right Capability.

Source verified · 2026-08-23Public site import · 2026-08-27