Skip to main content
Subagents are specialized AI agents that operate with their own custom system prompt and isolated context window. They handle specific tasks delegated by the main agent without polluting the main conversation context.

​
What You’ll Learn

  • Understanding default subagents
  • When to use each subagent
  • Manual invocation with @-mentions

​
Key Characteristics

  • Isolated Context: Each subagent maintains its own separate context window
  • Custom System Prompts: Every subagent has a dedicated system prompt defining its behavior
  • Manual Invocation: Users can explicitly reference subagents using @-mentions (@Verifier, @Code-reviewer)

​
Default Subagents

Verdent includes two built-in subagents that are pre-configured and immediately available.
Specialization: Quick code checks and validationCapabilities:
  • Validates code logic
  • Checks syntax correctness
  • Verifies implementation against requirements
Usage:
@Verifier check this authentication logic
Best For: Rapid validation without full code review overhead
@Verifier can be configured to use a different model in Settings. Use a smaller, cheaper model for simple verification tasks.

​
Using Subagents

​
Manual Invocation

Use @-mentions to explicitly invoke a subagent: 
@Code-reviewer review the security of login flow
@Verifier check validation logic in middleware
Benefits of Manual Invocation:
  • Precision: Ensure exact subagent handles the task
  • Control: Choose specific subagent when multiple could apply
  • Consistency: Repeat tasks with same subagent for consistent results

​
When to Use Each Subagent

Task TypeSubagentExample
Quick validation@Verifier@Verifier check this logic
Security review@Code-reviewer@Code-reviewer review auth flow
Code quality@Code-reviewer@Code-reviewer identify issues
Syntax check@Verifier@Verifier validate this function

​
Subagent vs Main Agent

AspectSubagentMain Agent
ContextIsolated, focusedFull conversation context
SpeedFaster for specific tasksBetter for complex analysis
Best forValidation, reviewInvestigation, implementation

​
FAQs

Use subagents for quick, focused tasks like validation or code review. Use the main agent for complex investigations requiring full context.
No. Subagents have isolated context windows. Only the final results are returned to the main agent.
Yes. @Verifier can be configured to use a different model in Settings for cost optimization.

​
See Also

Debugging

Using @Verifier for debugging workflows

Settings

Configure subagent models