# Agent Management

The Capsule Security platform provides comprehensive AI agent discovery, monitoring, and security management across multiple platforms.

## Supported AI Platforms

The platform integrates with leading AI agent platforms:

- **Microsoft**: CopilotStudio, PowerAutomate
- **Salesforce**: AgentForce
- **ServiceNow**: AgentSpace
- **AWS**: Bedrock
- **Azure**: Azure AI
- **Google Cloud**: Vertex AI
- **Automation Tools**: Zapier, UiPath, n8n
- **Enterprise**: Databricks, SAP, Box, Workato


## Agent Discovery

### Automatic Discovery

Once integrated, the platform automatically discovers and catalogs:

- All deployed AI agents
- Agent configurations and permissions
- Tools and capabilities
- Data sources and connections
- Ownership information
- Environment details


### Manual Registration

For custom or unsupported platforms, agents can be manually registered through the API:


```json
POST /api/v1/agents
{
  "name": "Custom Support Agent",
  "platform": "CUSTOM",
  "environment": "production",
  "owner": {
    "email": "owner@example.com"
  },
  "accessibility": "TENANT",
  "description": "Customer support automation agent",
  "tools": ["email", "database", "api"]
}
```

## Agent Search and Filtering

### Search Capabilities

The agent list page provides powerful search and filtering:


```javascript
GET /api/v1/agents?search=support&severity=HIGH&access=PUBLIC

// Filter parameters:
// - search: Text search in name and description
// - severity: LOW, MEDIUM, HIGH, CRITICAL
// - access: PUBLIC, TENANT, LIMITED
// - environment: production, staging, development
// - platform: COPILOTSTUDIO, POWERAUTOMATE, etc.
// - ownership: Owner email or ID
// - tools: Tool types used by agent
```

### Agent List View

The `AgentsList` component displays agents in a responsive grid:

- Visual severity indicators
- Platform icons
- Owner information
- Last activity timestamps
- Quick access to details
- Bulk action capabilities


## Agent Details

Each agent profile includes:

### Basic Information

- Agent name and description
- Platform and environment
- Owner details with contact info
- Creation and modification dates
- Unique identifiers (internal and external)


### Security Assessment

- **Accessibility Level**
  - PUBLIC: Accessible to anyone
  - TENANT: Restricted to tenant users
  - LIMITED: Specific user access only
- **Risk Severity**
  - Highest issue severity indicator
  - Number of open security issues
  - Compliance status


### Technical Details

#### Tools and Capabilities

Comprehensive list of tools the agent can access:

- Database connections
- API integrations
- File system access
- Email capabilities
- External service connections


#### Data Flow Visualization

Visual representation of:

- Data sources (nodes)
- Data connections (edges)
- Flow direction (ATOB, BTOA, BOTH)
- Security checkpoints


#### Usage Metrics

- Total session count
- Invocation frequency
- Last used timestamp
- Peak usage times
- User interaction patterns


## Security Issues Management

### Issue Categories

Issues are categorized by type:

- **Supply Chain**: Third-party dependency risks
- **Data**: Data exposure or leakage risks
- **Compliance**: Regulatory compliance violations
- **Integrity**: Data integrity concerns
- **Access**: Unauthorized access risks
- **Miscellaneous**: Other security concerns


### Issue Severity Levels

- **CRITICAL**: Immediate action required
- **HIGH**: Address within 24 hours
- **MEDIUM**: Address within 1 week
- **LOW**: Address in next maintenance cycle


### Issue Workflow

1. **Detection**: Automated scanning identifies issues
2. **Classification**: Issues categorized and prioritized
3. **Assignment**: Routed to appropriate team
4. **Resolution**: Fix implemented and tested
5. **Verification**: Issue confirmed resolved



```javascript
GET /api/v1/agents/{agentId}/issues?status=OPEN

// Issue statuses:
// - OPEN: Awaiting resolution
// - RESOLVED: Issue fixed
// - IGNORED: Accepted risk
```

## Agent Monitoring

### Real-time Monitoring

The platform provides continuous monitoring:

- Active session tracking
- Anomaly detection
- Performance metrics
- Error rate tracking
- Resource utilization


### Session Timeline

Visualize agent activity over time:

- Session frequency
- Duration patterns
- User interactions
- Peak usage periods
- Trend analysis


## Best Practices

### Agent Governance

1. **Ownership Assignment**
  - Every agent must have a designated owner
  - Owners responsible for security compliance
  - Regular ownership reviews
2. **Access Control**
  - Follow principle of least privilege
  - Regular access reviews
  - Document access requirements
3. **Tool Management**
  - Minimize tool permissions
  - Regular capability audits
  - Remove unused integrations


### Security Recommendations

1. **Regular Audits**
  - Weekly security issue reviews
  - Monthly compliance checks
  - Quarterly architecture reviews
2. **Issue Resolution**
  - Prioritize CRITICAL and HIGH severity
  - Document resolution steps
  - Implement preventive measures
3. **Monitoring**
  - Set up alerting for anomalies
  - Track usage patterns
  - Monitor for unauthorized access


## Troubleshooting

### Common Issues

1. **Agents Not Appearing**
  - Verify integration is connected
  - Check sync status
  - Review platform permissions
  - Wait for next sync cycle
2. **Missing Agent Details**
  - Ensure platform API permissions
  - Check network connectivity
  - Review error logs
3. **Incorrect Severity Ratings**
  - Refresh agent assessment
  - Review issue detection rules
  - Contact support for calibration