Create and Edit Cloud Agents - Continue

<Card title="Creating Custom Cloud Agents" icon="wrench"> You can only create and edit AI Agents in the Continue Mission Control web interface. This ensures proper validation, versioning, and team collaboration features. </Card>

Creating a Cloud Agent

<Steps> <Step title="🧭 Navigate to Create Agent"> Navigate to the [New Agent page](https://continue.dev/agents/new). </Step> <Step title="🧩 Fill Out the Agent Form"> Configure your Cloud Agent with the following fields:

| Field | What to Enter | Example |
|-------|---------------|---------|
| **Name** | Display name shown in Mission Control | `GitHub PR Agent` |
| **Prompt** | First instruction the agent receives | `Open a GitHub PR to fix the specified issue.` |
| **Tools ([MCPs](https://continue.dev/hub?type=mcpServers))** | Select built-in or custom MCPs | `GitHub, PostHog, Supabase, etc.` |
| **[Rules](https://continue.dev/hub?type=rules)** | Add any organizational rules | `continuedev/gh-pr-commit-workflow` |
| **[Model](https://continue.dev/hub?type=models)** | Choose a default LLM | `Claude Sonnet 4.5` |
| **Trigger** | Determines when the cloud agent will be invoked | `GitHub, cron, webhook` |


<Info>
  **Tip**: Start with a simple prompt and add complexity through rules and tools. The prompt should be a clear, single instruction that defines the AI Agent's primary goal.
</Info>

</Step> <Step title="💡 Choose Repository & Automation"> In the right panel, you can select the repository where the agent will run, and decide if the agent should automatically kick off on creation. </Step> <Step title="✅ Create and Test"> Click **"Create Agent"** to save and publish it.

Your agent is immediately available to run in:
- Mission Control web interface
- TUI mode: `cn --agent your-org/your-agent-name`
- Headless mode: `cn --agent -p your-org/your-agent-name "prompt" --auto`

</Step> </Steps>

Editing a Cloud Agent

You can edit any AI Agent you own or that has Organization-level access.

From the Agents page, click your agent's name. Change any of the fields in the edit form, then click "Save Changes".

Example Agent Configurations

Here are proven agent configurations you can create or use as inspiration:

<CardGroup cols={2}> <Card title="Security Scanner Cloud Agent" icon="shield" href="https://continue.dev/continuedev/snyk-continuous-ai-agent"> **Snyk Continuous AI Agent** - Comprehensive security scanning with Snyk MCP integration.

Automates dependency analysis, vulnerability scanning, and creates remediation PRs with Cloud Agent powered fix suggestions.

</Card> <Card title="Performance Monitoring Cloud Agent" icon="gauge" href="https://continue.dev/continuedev/netlify-continuous-ai-agent"> **Netlify Continuous AI Agent** - Performance optimization with A/B testing and monitoring.

Cloud Agent tracks Core Web Vitals, identifies regressions, and provides optimization recommendations.

</Card> <Card title="Error Monitoring Agent" icon="bug" href="https://continue.dev/continuedev/sentry-continuous-ai-agent"> **Sentry Continuous AI Agent** - Automated error analysis and issue creation.

Monitors production errors, provides root cause analysis, and creates actionable GitHub issues.

</Card> <Card title="GitHub Management Cloud Agent" icon="github" href="https://continue.dev/continuedev/github-manager-ai-agent"> **GitHub Manager AI Agent** - Comprehensive GitHub workflow automation.

Handles issue triage, PR reviews, and release note generation with natural language prompts.

</Card> <Card title="Database Management Cloud Agent" icon="database" href=" https://continue.dev/continuedev/supabase-agent"> **Supabase Continuous AI Agent** - Database security and management workflows.

Audits Row Level Security, identifies vulnerabilities, and generates fixes automatically.

</Card> </CardGroup>

Troubleshooting

Common issues and solutions:

Problem	Solution
Cloud Agent doesn't complete tasks	Simplify the prompt, add more specific instructions, verify tool permissions
Tools aren't working	Check MCP configuration, verify API keys and permissions in Hub settings
Inconsistent behavior	Add rules to enforce consistent patterns, test with various input scenarios
Performance issues	Consider model choice, simplify complex multi-step workflows, optimize tool usage