> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.agenttrunk.ai/concepts/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.agenttrunk.ai/_mcp/server.

# Core concepts

## Docs

- [Organizations and workspaces](https://docs.agenttrunk.ai/concepts/workspaces.md): Separate your team's access boundary from each agent's context.
- [Context, revisions, and releases](https://docs.agenttrunk.ai/concepts/revisions.md): Know what moves, what is immutable, and what to pin for a run.
- [Permissions and agent access](https://docs.agenttrunk.ai/concepts/permissions.md): Agents act for their humans, with explicit access to context and releases.
- [Share context across workspaces](https://docs.agenttrunk.ai/concepts/context-sets.md): Compose pinned sources without duplicating policies or bypassing access.