Capability System

The Capability System defines what agents can do, mapping skills and components to granular permissions that enable governance and maturity-based access control.

Overview

Capabilities bridge the gap between agent skills and governance, providing fine-grained control over what actions agents can perform based on their maturity level and training.

Core Concepts

What are Capabilities?

Capabilities are specific actions or permissions that agents can perform. Examples include:

Data Operations: Query databases, generate reports, create visualizations
Code Execution: Run scripts, access terminal, execute commands
Integrations: Make API calls, handle webhooks, connect to external services
Communication: Send emails, post messages, trigger notifications

Capability Types

Type	Purpose	Examples
Tool	Access to specific features	Chart rendering, code editor, data visualization
Action	Specific operations	API calls, data queries, webhook triggers
Permission	Sensitive operations	Shell access, database writes, system configuration

Functional Domains

Capabilities are organized by domain:

Domain	Focus	Example Capabilities
Data Analysis	Analytics and reporting	Data visualization, chart generation, dashboard creation
Code Execution	Running code and scripts	Code execution, command line, file operations
Integrations	External service connections	API calls, webhooks, data connectors
Communication	Messaging and notifications	Email, Slack, SMS, in-app notifications
Automation	Workflow and scheduling	Triggers, scheduled tasks, automation rules

How Capabilities Work

Capability Assignment

When an agent is created, it receives capabilities based on:

Installed Skills: Each skill provides specific capabilities
Canvas Components: UI components grant related capabilities
Agent Maturity: Higher maturity levels unlock more capabilities

Governance Enforcement

Before an agent performs an action, the system checks:

Capability Existence: Does the agent have this capability?
Maturity Check: Is the agent's maturity level sufficient?
Rate Limits: Has the agent exceeded usage quotas?
Tenant Permissions: Is the capability allowed for this tenant?

Capability Inference

The system automatically discovers capabilities from:

Component Analysis: Examines what canvas components do
Skill Metadata: Extracts capability information from skill definitions
Usage Patterns: Learns from actual agent behavior

Usage Patterns

Granting Capabilities

Capabilities are typically granted automatically when:

Installing a skill: The skill's capabilities are added to the agent
Adding canvas components: Component capabilities are inferred
Promoting maturity: Higher maturity unlocks additional capabilities

Checking Permissions

Before executing actions, agents verify they have the required capability:

Agent wants to execute code
    ↓
Check: Does agent have "code_execution" capability?
    ↓
Check: Is agent maturity ≥ "supervised"?
    ↓
Check: Is code execution within rate limits?
    ↓
Execute or Deny

Capability Profiling

Track agent capabilities by:

Domain Coverage: Which functional domains the agent operates in
Proficiency Level: How skilled the agent is with each capability
Usage Frequency: How often capabilities are used
Success Rate: Success vs. failure ratios

Maturity and Capabilities

Different maturity levels have different capability access:

Maturity	Capability Access	Governance
Student	Read-only capabilities	Observation only
Intern	Basic capabilities with approval	Requires approval for actions
Supervised	Most capabilities	Live monitoring, can queue if unavailable
Autonomous	All capabilities	Self-directed, can supervise others

Capability Marketplace

Share and discover capabilities across tenants:

Capability Templates: Pre-defined capability sets for common use cases
Best Practices: Learn how others structure capabilities
Cross-Tenant Sharing: Reuse capability definitions (with governance)

API Overview

Capability Management

List all available capabilities
Get details about specific capabilities
Create custom capabilities
Update capability definitions

Agent Capabilities

View agent's assigned capabilities
Add capabilities to agents
Remove capabilities from agents
Check if agent can perform specific action

Capability Matrix

View capability matrix across all agents
Get agent capability profile
Check domain proficiency
Analyze capability usage patterns

Capability Feedback

Submit feedback on capability execution
View capability success rates
Identify capabilities needing improvement

Best Practices

Start Small: Grant minimal capabilities, expand as agent proves competence
Domain Alignment: Group related capabilities under appropriate domains
Monitor Usage: Track which capabilities are used most/least
Regular Reviews: Periodically audit and update capability assignments
Progressive Expansion: Add capabilities as agents demonstrate success

Common Scenarios

Creating a Data Analyst Agent

Required Capabilities:
- data_visualization (tool)
- chart_rendering (tool)
- data_query (action)
- report_generation (action)

Required Maturity: Intern or higher

Domain: Data Analysis

Creating an Integration Specialist

Required Capabilities:
- api_call (action)
- webhook_handler (action)
- data_connector (tool)
- authentication_management (permission)

Required Maturity: Supervised or higher

Domain: Integrations

ATOM Documentation