Starting with Cloud Agents - Continue

<Card title="🚀 Quick Start with Mission Control" icon="rocket"> Mission Control is your web interface for running and managing Cloud Agents. Get started in minutes with pre-built workflows for security scanning, GitHub management, analytics insights, and more. </Card> <Info> Mission Control is in beta. Please share any feedback with us in [GitHub discussions](https://github.com/continuedev/continue/discussions/8051). </Info>

Use Mission Control to kick off Cloud Agents for:

Bug fixes & code quality - Address nitpicks and technical debt
Feature development - Build boilerplate-heavy features
Security & compliance - Automated vulnerability scanning
Investigation & analysis - Research issues to kickstart your work
Custom workflows - Run repeatable tasks with your own rules and prompts

Quick Start

<Tip> If you haven't already, create an account and connect your GitHub repositories in [Mission Control](https://continue.dev/). </Tip> <Steps> <Step title="Navigate to Your Agents Page"> Go to [Mission Control Agents page](https://continue.dev/agents) and select an existing workflow with a pre-configured Cloud Agent. </Step> <Step title="Run Your First Cloud Agent"> Your agents page lists all available Cloud Agents. Click on the agent and then **Test Run** to start it. </Step> </Steps> <Info> **New to agents?** Check out our [pre-configured agents](/mission-control/beyond-checks) to test out a workflow immediately. </Info>

Try a Cloud Agent First: Your 60-Second Challenge

Before creating your own agent, let's see one in action! The fastest way to experience the power of Continue agents is with our demo repository.

See an Agent Create a Pull Request in Under 60 Seconds

<Steps> <Step title="🍴 Fork Our Demo Repository"> Get a safe sandbox to experiment with:

**Option 1: GitHub Web Interface**
Visit [github.com/continuedev/demo-project](https://github.com/continuedev/demo-project) and click **Fork**

**Option 2: GitHub CLI**
```bash
gh repo fork continuedev/demo-project
```

</Step> <Step title="🎯 Access Mission Control"> Go to [Mission Control](https://continue.dev/) and: - **Connect GitHub** and authorize Continue when prompted - This gives agents access to create PRs in your repositories </Step> <Step title="🚀 Run Your First Agent"> **Target your forked demo repo** and try one of these commands as a [task](../mission-control/tasks):

<Tabs>
  <Tab title="Add New Feature">
    ```
    Create a new function that calculates fibonacci numbers.
    ```
  </Tab>
  
  <Tab title="Fix Existing Bug">
    ```
    Fix the TypeError in api/users.ts
    ```
  </Tab>
  
  <Tab title="Add Documentation">
    ```
    Add comprehensive README documentation with setup instructions.
    ```
  </Tab>
</Tabs>

</Step> <Step title="✨ Watch the Magic"> **Result:** A fully-formed Pull Request opens in your demo repo with: - Complete implementation or fix - Proper commit messages - Detailed PR description - Ready for review and merge </Step> </Steps> <Info> **Why Use the Demo Repo?** - **Safe testing environment** - No risk to your production code - **Pre-configured issues** - Common bugs and features to practice with - **Immediate results** - See agents in action without setup complexity - **Learn by example** - Study the generated code and PR descriptions </Info> <Tip> Once you see how agents work with the demo repo, you'll understand exactly how to create and customize your own for real projects! </Tip>

Example Workflow Tasks

Here are some example tasks you can try with your Cloud Agents:

- "Fix the TypeError in api/users.ts where the user object might be undefined"
- "Add null checks to all database query results in the services/ directory"
- "Fix all ESLint warnings in the components folder and open a PR"
- "Update deprecated React lifecycle methods to hooks in legacy components"

</Accordion> <Accordion title="Feature Development">

- "Create a new REST endpoint for user profile updates with validation and error handling"
- "Add pagination to the products list page with previous/next buttons"
- "Implement dark mode toggle using Tailwind CSS classes across all pages"
- "Add unit tests for the authentication service using Jest"

</Accordion> <Accordion title="Security & Compliance">

- "Run a complete security scan and create GitHub issues for critical vulnerabilities"
- "Scan the codebase for hardcoded API keys and move them to environment variables"
- "Add input sanitization to all user-facing form fields"
- "Update npm packages with security vulnerabilities and test compatibility"

</Accordion> <Accordion title="Documentation & Boilerplate">

- "Add JSDoc comments to all exported functions in the utils/ directory"
- "Create a README.md for the new payment-processing module with setup instructions"
- "Generate TypeScript interfaces for all API response schemas"
- "Add error handling boilerplate to all async functions missing try-catch blocks"

</Accordion> <Accordion title="Investigation & Analysis">

- "Investigate why the login API is returning 500 errors intermittently and suggest fixes"
- "Analyze the performance bottleneck in the data processing pipeline"
- "Review the database schema for the orders table and suggest optimizations"
- "Find all TODO comments related to authentication and create a summary"

</Accordion> <Accordion title="Refactoring">

- "Extract the repeated validation logic in controllers into a shared utility function"
- "Convert all class components in src/legacy to functional components with hooks"
- "Rename all instances of 'userId' to 'accountId' across the codebase"
- "Split the 500-line UserService.ts into smaller, single-responsibility services"

</Accordion> </AccordionGroup>

Ways to Run Cloud Agents

Choose the method that fits your workflow:

<Tabs> <Tab title="🌐 Mission Control"> **Web interface for interactive use**

Perfect for:
- Exploring AI agent capabilities
- Reviewing outputs before action
- Monitoring ongoing workflows
- Team collaboration
- One-time tasks

Access at [continue.dev/agents](https://continue.dev/agents)

</Tab> <Tab title="💻 CLI (TUI Mode)"> **Terminal interface for development**

```bash
cn --agent continuedev/github-project-manager-agent
```

Perfect for:
- Local development workflows
- Testing agent behavior
- Interactive debugging
- Quick iterations

</Tab> <Tab title="🤖 Headless Mode"> **Automated execution for CI/CD**

```bash
cn --agent continuedev/snyk-continuous-ai-agent -p "Run security scan" --auto
```

Perfect for:
- Scheduled workflows
- CI/CD integration
- Webhook triggers
- Background processing

</Tab> </Tabs>

Best Practices for Cloud Agent Success

The practice of using Cloud Agents (Continuous AI) requires thoughtful setup of guardrails and habits:

<CardGroup cols={2}> <Card title="Start Small" icon="seedling"> Begin with tasks you're confident Continue can handle, like fixing known bugs with simple solutions. </Card> <Card title="Practice Locally" icon="terminal"> Test with [Continue CLI](../guides/cli) in TUI mode before deploying automation. </Card> <Card title="Be Thorough" icon="clipboard-list"> Agents can run for extended periods - invest time in detailed prompts with all important context. </Card> <Card title="Team Alignment" icon="users"> Discuss agent usage and adjust code review habits for higher PR volumes. </Card> </CardGroup> <Info> **Learn More**: Explore advanced patterns and case studies on the [Continuous AI Blog](https://blog.continue.dev). </Info>