What You’ll Learn
This section covers Verdent’s power-user capabilities including subagent management, rule systems, tool integration, parallel execution, and advanced extensibility options.Complex Feature Explanations
Verdent provides sophisticated features that enable advanced development workflows beyond basic code generation.Subagent System
Specialized AI Agents: Verdent includes a built-in subagent:@verifier for code verification and quick checks. Subagents operate with isolated context windows and custom system prompts, specializing in specific tasks.
Manual Invocation:
Use @-mentions to invoke subagents (e.g., @verifier check this function). This delegation preserves main context while handling specialized operations efficiently.
Learn more about subagent management
Rule Systems
Behavior Customization: Rule files guide Verdent’s behavior, output formatting, and decision-making through plain Markdown documents. Two rule types control different scopes:- VERDENT.md - Global personal preferences across all projects (Settings → User Rules)
- AGENTS.md - Project-specific team standards (version controlled)
AGENTS.md) override user rules, ensuring team consistency while preserving personal preferences for solo projects.
Learn more about rule systems
Tool System & MCP
Built-in Tools: Verdent provides comprehensive tools for file operations, search (glob/grep), command execution (bash), web access, and agent delegation. Tools enable all code manipulation, navigation, and external interaction.
Model Context Protocol (MCP):
MCP extends Verdent’s capabilities by connecting to external tools, data sources, and services. Configure MCP servers through Settings → MCP Servers to integrate project-specific APIs and custom functionality.
View tool reference
Learn about MCP integration
Multi-Agent Coordination
Verdent’s multi-subagent architecture enables parallel task execution with automatic routing and coordination. Main Agent (Orchestrator): The primary agent analyzes requests, breaks down complex tasks, and delegates specialized work to subagents while maintaining conversation context and consolidating results. Parallel Execution: Multiple agents can run concurrently in separate workspaces. Each workspace has its own isolated environment, enabling true parallel development without conflicts. Context Isolation: Each agent operates with its own context window. This isolation prevents context exhaustion during multi-step operations and ensures parallel work doesn’t interfere. Subagent Usage: Built-in subagents can be invoked for specialized tasks:- Validation checks →
@verifier
Desktop-Specific Advanced Features
Parallel Agents in Workspaces
Verdent uniquely supports running multiple AI agents simultaneously across git workspaces (worktrees):| Feature | Capability |
|---|---|
| Independent Agents | Each workspace can have its own active agent |
| Isolated Contexts | Agents don’t share context between workspaces |
| Parallel Execution | Work on multiple features simultaneously |
| Coordinated Rebasing | Review and rebase parallel work to main branch |
Advanced Context Management
Desktop-specific context optimization:- Workspace Strategy
- Subagent Delegation
- Task Management
- Use separate workspaces for independent features
- Each workspace maintains isolated context
- Rebase to main branch when features are complete
- Clean up workspaces to free resources
Custom Workflow Creation
Advanced users can customize Verdent’s behavior to match team processes and project requirements. Rule-Based Customization: Define coding standards, testing requirements, and output preferences through rule files:- Enforce team conventions (indentation, naming, patterns)
- Specify documentation styles and comment detail levels
- Configure user preferences globally or per-project
- Database query tools
- Cloud service APIs (AWS, Azure, GCP)
- Project management integrations (Jira, Linear)
- CI/CD pipeline connections