Skip to main content
Last updated on

Agents

Agents are the core entity in OpenBox. Each agent represents an AI system (workflow, assistant, or autonomous process) that OpenBox governs.

Access the agent list from the sidebar by clicking Agents.

Agents

Stats Cards

The top of the page shows three key metrics:

MetricDescription
Total AgentsTotal registered agents with monthly change
Guardrail Violation RatePercentage of operations blocked by guardrails
Policy Violation RatePercentage of operations blocked by policies

Search and Filters

Filter the agent list using:

  • Search - Find agents by name or ID
  • Trust Tier - Filter by Tier 1, 2, 3, or 4
  • Status - Active, Inactive, or Revoked
  • Team - Filter by owning team

Agent Table

The main table displays:

ColumnDescription
AgentName, icon, and ID
StatusActive (green pulse), Inactive, or Revoked
Trust TierTIER 1, TIER 2, TIER 3, or TIER 4 badge
Trust ScoreCurrent 0-100 score with trend indicator (↑/↓)
TeamOwning team
Violations 24hNumber of violations in the last 24 hours
VerificationReal-time attestation status
Last ActiveTime since last activity
ActionsMenu for View Details, Settings

Status Indicators

StatusIndicator
ActiveGreen badge with pulsing dot
InactiveGray badge
RevokedRed badge

Trust Tier Badges

TierColorDescription
TIER 1GreenTier 1 (0% – 24%): Trusted — Minimal oversight, broad permissions
TIER 2BlueTier 2 (25% – 49%): Confident — Standard controls, approval for sensitive ops
TIER 3OrangeTier 3 (50% – 74%): Monitor — Strict controls, monitoring required
TIER 4RedTier 4 (75% – 100%): Restrict — Minimal permissions, approval for most ops

Agent Actions

Click the menu on any row to:

  • View Details - Navigate to agent detail page
  • Settings - Go directly to agent settings

Or click anywhere on the row to view the agent detail.

Adding Agents

Click the Add Agent button (top right) to register a new agent. See Registering Agents for details.

Agent Detail Page

Click any agent to view its detail page with these tabs:

  • Overview - Active sessions, completed, failed, and halted sessions
  • Assess - Risk profile configuration
  • Authorize - Guardrails, policies, and behavioral rules
  • Monitor - Operational dashboard and telemetry
  • Verify - Goal alignment and drift detection
  • Adapt - Trust evolution and policy suggestions
  • Settings - Agent configuration, risk profile, API keys, and lifecycle management

Next Steps

  1. Register a New Agent - Add a new agent to OpenBox
  2. Trust Overview - View trust scores and trends across all agents