---
title: Writing New Code
description: "Using Verdent to write and generate code effectively"
---

Learn how to write effective prompts, use @-mentions for context, and select the right model preset for code generation.

## What You'll Learn

- Compose effective prompts for code generation
- Use @-mentions to provide context
- Leverage Desktop-specific features for parallel development
- Review generated code with Code Review

---

## Prompt Composition

### Effective Prompt Structure

<Tabs>
  <Tab title="Simple Tasks">
    For straightforward code generation:

    ```
    Create a function that [does X]
    ```

    **Example:**
    ```
    Create a function that validates email addresses using regex
    ```
  </Tab>
  <Tab title="Complex Tasks">
    For multi-step or complex code:

    ```
    I need to [goal]. The context is [background].
    Requirements:
    - [Requirement 1]
    - [Requirement 2]

    Consider [constraints or preferences]
    ```

    **Example:**
    ```
    I need to build a user authentication system. We're using Express.js with PostgreSQL.
    Requirements:
    - JWT-based authentication
    - Refresh token support
    - Password hashing with bcrypt

    Follow the existing patterns in our auth middleware
    ```
  </Tab>
  <Tab title="Best Practices">
    **Do:**
    - Be specific about desired behavior
    - Mention relevant files or patterns
    - Specify error handling expectations
    - Include edge cases to handle

    **Don't:**
    - Use vague language ("make it better")
    - Assume context from previous sessions
    - Leave out important constraints
    - Request multiple unrelated changes
  </Tab>
</Tabs>

### Iterative Development

Build features incrementally:

<Steps>
  <Step title="Start Simple">
    Request the basic structure or core functionality first
  </Step>
  <Step title="Review and Refine">
    Review generated code, request specific improvements
  </Step>
  <Step title="Add Complexity">
    Layer in error handling, edge cases, validation
  </Step>
  <Step title="Test and Polish">
    Request tests, documentation, or final polish
  </Step>
</Steps>

---

## Using @-Mentions

@-mentions provide context by referencing specific files, folders, or symbols.

### Syntax

| Mention | Scope | Example |
|---------|-------|---------|
| `@filename` | Single file | `@userService.ts` |
| `@folder/` | Directory | `@src/components/` |

### When to Use @-Mentions

<Tabs>
  <Tab title="Explicit Context">
    ```
    Look at @authMiddleware.ts and create a similar middleware for rate limiting
    ```
  </Tab>
  <Tab title="Multiple Files">
    ```
    Refactor @userController.ts to use the patterns from @productController.ts
    ```
  </Tab>
  <Tab title="Folder Scope">
    ```
    Search @src/utils/ for any duplicate utility functions
    ```
  </Tab>
</Tabs>

---

## Desktop-Specific Code Writing

### Parallel Feature Development

<Tabs>
  <Tab title="Independent Features">
    Build unrelated features simultaneously in separate workspaces:

    <Steps>
      <Step title="Create First Workspace">
        Click **New Workspace** in the Top Bar to create an isolated workspace for your first feature
      </Step>
      <Step title="Name the Workspace">
        Give the workspace a descriptive name (e.g., "feature-auth")
      </Step>
      <Step title="Start a Task">
        In the input box, describe what you want to build and send your message to start a new task
      </Step>
      <Step title="Create Additional Workspaces">
        Repeat the above steps for each additional feature you want to work on
      </Step>
      <Step title="Work in Parallel">
        Each agent works independently in its own workspace without conflicts
      </Step>
      <Step title="Review Changes">
        When a feature is complete, review changes
      </Step>
      <Step title="Rebase to main branch">
        Click **Workspace Actions → Rebase to main branch** to apply changes
      </Step>
    </Steps>

    **Example:** Build an authentication system in one workspace while another agent builds the dashboard UI in a separate workspace.
  </Tab>
  <Tab title="Bug Fix + Feature">
    Fix urgent bugs without interrupting ongoing feature development:

    <Steps>
      <Step title="Continue Feature Work">
        Keep your current feature work running in its workspace
      </Step>
      <Step title="Create Bug Fix Workspace">
        Click **New Workspace** in the Top Bar to create a separate workspace for the bug fix
      </Step>
      <Step title="Name the Workspace">
        Name the workspace descriptively (e.g., "fix-login-error")
      </Step>
      <Step title="Describe the Bug">
        In the input box, describe the bug and how to fix it to start a new task
      </Step>
      <Step title="Parallel Work">
        The bug fix agent works independently while your feature agent continues
      </Step>
      <Step title="Ship the Fix">
        When the fix is ready, click **Workspace Actions → Rebase to main branch** to ship the fix
      </Step>
      <Step title="Resume Feature Work">
        Your feature workspace continues uninterrupted with the fix now in master
      </Step>
    </Steps>

    **Benefit:** Ship critical fixes immediately without pausing feature development or losing context.
  </Tab>
  <Tab title="Experimental">
    Try risky refactors or experimental approaches without affecting stable code:

    <Steps>
      <Step title="Create Experiment Workspace">
        Click **New Workspace** in the Top Bar to create an isolated workspace for your experiment
      </Step>
      <Step title="Name the Workspace">
        Name it clearly (e.g., "experiment-new-architecture")
      </Step>
      <Step title="Describe the Experiment">
        In the input box, describe the experimental approach you want to try to start a new task
      </Step>
      <Step title="Let Agent Explore">
        Let the agent explore and implement the changes freely
      </Step>
      <Step title="Review Results">
        Review the results to see all modifications
      </Step>
      <Step title="Keep or Discard">
        If successful, click **Workspace Actions → Rebase to main branch** to keep changes. If failed, click **Delete Workspace** in the Workspace Bar to discard all changes.
      </Step>
    </Steps>

    **Benefit:** Your base workspace remains stable and unchanged regardless of experimental outcomes.
  </Tab>
</Tabs>

### Plan Mode for Complex Features

For complex code generation:

1. Press `Shift+Tab` or `Ctrl+.` to switch to **Plan Mode**
2. Describe the feature you want to build
3. Review the plan Verdent creates
4. Refine with follow-up questions
5. Switch to **Agent Mode** to execute the plan

**Benefit:** Review approach before consuming credits on execution.

### Reviewing Generated Code

After Verdent generates code, use Code Review for quality assurance:

<Steps>
  <Step title="View Code Review">
    After Verdent completes changes, the Code Review panel appears inline within the chat
  </Step>
  <Step title="Address Critical Issues">
    Review **Must Fix** items first, these are security, performance, or stability issues
  </Step>
  <Step title="Consider Suggestions">
    Review **Suggestions** for recommended improvements you may want to apply
  </Step>
  <Step title="Request Fixes">
    Ask Verdent to fix any issues by describing what needs to change in the input box
  </Step>
  <Step title="View Diff">
    Click **Task Changes** in the middle panel to see all file modifications
  </Step>
</Steps>

**Code Review analyzes:**

| Category | Focus |
|----------|-------|
| **Security** | Vulnerability scanning, injection risks, credential exposure |
| **Accessibility** | Accessibility compliance and best practices |
| **Performance** | Algorithmic complexity, resource usage |
| **Call-chain Impact** | Downstream effects on dependent code |

<Tip>
Enable **Auto Generate Code Review** in Settings → Chat to automatically generate reviews after every change.
</Tip>

---

## FAQs

<Accordion title="How do I get more accurate code generation?">
1. **Be specific** - Include exact requirements
2. **Provide context** - Use @-mentions for relevant files
3. **Specify patterns** - Reference existing code as examples
4. **Iterate** - Build incrementally rather than all at once
</Accordion>

<Accordion title="Should I use Plan Mode for all code writing?">
Use Plan Mode for:
- Complex multi-file changes
- Unfamiliar patterns or codebases
- When you want to review approach first

Skip Plan Mode for:
- Simple, straightforward tasks
- Well-understood changes
- Quick iterations
</Accordion>

<Accordion title="Can I work on multiple features at the same time?">
Yes. Create separate workspaces for each feature by clicking **New Workspace** in the Top Bar. Each workspace has its own agent working in isolation.
</Accordion>

<Accordion title="How do I undo changes Verdent made?">
You don't need to delete the entire workspace to undo changes. You have several options:

- **Rollback:** Hover over any message in the chat and click **Rollback to this point** to revert to an earlier state.
- **Use Source Control:** Open Source Control (`Ctrl+Shift+G` / `Cmd+Shift+G`) to view changed files and revert specific changes.
- **Delete workspace:** Click **Delete Workspace** in the Workspace Bar to discard all changes in that workspace. Your base workspace remains unaffected.
</Accordion>

<Accordion title="Does Code Review use credits?">
Yes. Code reviews consume credits based on the amount of code analyzed. Disable auto-review in Settings → Chat if you want to save credits.
</Accordion>

<Accordion title="Can Verdent generate tests for my code?">
Yes. Ask Verdent to write tests by describing what to test and referencing files with @-mentions (e.g., "Write tests for @userService.ts").
</Accordion>

---

## See Also

<CardGroup cols={2}>
  <Card title="Code Review" icon="magnifying-glass" href="/docs/verdent/core-features/code-review">
    Auto-generated quality assessment
  </Card>
  <Card title="Refactoring" icon="code" href="/docs/verdent/task-based-guides/refactoring">
    Safe refactoring workflows
  </Card>
  <Card title="Best Practices: Prompts" icon="lightbulb" href="/docs/verdent/best-practices/prompts">
    Prompt engineering tips
  </Card>
</CardGroup>