Agents Overview

Standardized AI workflows that combine prompts, rules, and tools to complete specific, repeatable tasks

Agents in Continue

Agents are custom AI workflows that combine a prompt, rules, and tools (MCPs and more) to complete specific, repeatable tasks. They live in the Continue Hub and can be executed from Mission Control (web interface), TUI mode, or headless automation.

What Are Agents?

Agents let your team standardize common workflows like opening GitHub PRs, summarizing analytics, or auditing security. Each agent includes:

Agent Components

Component	Description	Example
Prompt	The agent’s main instruction that defines what it does and how it should behave. Additional user input is appended when invoked.	Example prompt: “Summarize ongoing work with status, blockers, and next steps. Use markdown formatting and a concise, professional tone.”
Rules	Define consistent standards or behaviors that guide how the agent responds. Rules help ensure reliability across team usage.	“Always include related issue or PR links when summarizing work.”
Tools / MCPs	External systems or integrations the agent can call to complete tasks. MCPs (Model Context Protocols) extend functionality through APIs.	GitHub, PostHog, Supabase
Model	The large language model that powers the agent’s reasoning and output generation.	Claude Sonnet 4.5
Visibility	Determines who can view or use the agent. Controls access at creation time.	Public, Organization, or Private

Mission Control is in beta. Please share any feedback with us in GitHub discussions.

Ways to Run Agents

You can run Agents in three main ways:

🌐 Mission Control

Interactive web interface

Trigger from the Continue Hub and review results in real-time.

# Navigate to hub.continue.dev/agents
# Click "Run Agent" on any agent
# Monitor progress and review outputs

Perfect for: Interactive debugging, reviewing agent outputs, team collaboration

Pre-configured Agents

Skip the setup and use battle-tested agents from our cookbook collection:

🔒 Security Scanning

continuedev/snyk-continuous-ai-agent Finds vulnerabilities and opens PRs with fixes

🐛 GitHub Management

continuedev/github-project-manager-agent Triages issues and manages project workflows

📊 Analytics Insights

continuedev/posthog-continuous-ai-agent Analyzes user data and creates actionable tasks

⚡ Performance Optimization

continuedev/netlify-continuous-ai-agent Monitors Core Web Vitals and optimizes deployments

🗄️ Database Auditing

continuedev/supabase-agent Audits RLS security and generates migrations

🔄 Data Pipelines

continuedev/dlt-agent Inspects pipelines and debugs load errors

Explore More Agents: Browse the complete collection of pre-configured agents and MCP integration cookbooks in our Guides Overview.

Collaboration

Agents are organizational assets — once created, everyone in your org can use them:

Role	Permissions
Public	Use, create, remix, and delete Agents
Organization	Share agents with your team
Private	Create, edit, and delete Agents for your personal use

Getting Started

1. Try a Pre-configured Agent

   Start with a cookbook agent like continuedev/github-project-manager-agent:

   cn --agent continuedev/github-project-manager-agent "List open issues labeled bug"
   

2. Practice with TUI Mode

   Test agents locally before automation:

   cn --agent continuedev/snyk-continuous-ai-agent
   # Interactive mode - perfect for learning how to use the agent for your use case
   

3. Create Your First Agent

   Ready to build custom workflows? Learn how in our Create and Edit guide.

4. Set Up Automation

   Integrate with CI/CD using headless mode and webhooks for continuous workflows.

Best Practices

The practice of using background agents, which we call Continuous AI, requires forethought to set up the right guardrails:

• Start Small: Begin with tasks you’re confident Continue can accomplish
• Use Thorough Prompts: Agents can run for extended periods, so invest in detailed instructions
• Test Locally First: Practice with TUI mode before deploying to production
• Team Alignment: Discuss agent usage and adjust code review habits for higher PR volume
• Iterate and Improve: Be willing to refine prompts based on results

Next Steps

Create an Agent

Build your first custom agent with prompts, rules, and tools

Explore Cookbooks

Browse pre-built agents for security, analytics, and more

CLI Guide

Learn to run agents from the command line

Mission Control

Access the web interface to manage agents