Dashboard

The Agent Keeper dashboard gives security teams one control plane for AI agent usage across workstations, repositories, and identity groups.

Main Views

• Posture: live posture, blocked actions, warning trends, and high-risk sessions.
• Workstations: connected Claude Code, Cursor, Codex, Gemini CLI, Windsurf, Copilot, and Cowork clients.
• Activity: searchable event stream for tool calls, policy decisions, and shield detections.
• Policies: org defaults, agent-specific controls, MCP restrictions, and group overrides.
• Investigations: suspicious sessions grouped into reviewable timelines.
• Settings: API keys, notification routing, telemetry setup, billing, and team management.

Event Model

Each agent event captures:

• Tool name and normalized action.
• Verdict: allowed, warned, or blocked.
• Detection pattern and severity when applicable.
• Session, repository, branch, host, and identity context when available.
• Policy source, including group overrides.

Operational Flow

1. Connect the first workstation from /setup.
2. Review the first events in /activity.
3. Tighten Runtime Shield and tool policies in /team-overview?tab=policies.
4. Add identity-provider groups when the team needs role-specific controls.
5. Use /security and /investigations for ongoing review.