Deploy Dome

​

What Developers Need

1. Install the package: Add vijil-dome to your Python dependencies, following Install Dome
2. Wrap LLM calls: Insert Guard checks before and after your agent’s LLM interactions
3. Configure Guards: Load configuration from the Vijil Console or define it in code
4. Handle blocked content: Return safe responses when Guards trigger

​

Integration Pattern

from vijil_dome import Dome

dome = Dome.create_from_vijil_agent(
    agent_id="your-agent-id",
    api_key="your-api-key"
)

def protected_chat(user_message: str) -> str:
    # Guard the input
    input_scan = dome.guard_input(user_message)
    if not input_scan.is_safe():
        return input_scan.guarded_response()

    # Your existing agent logic here
    response = your_agent.generate(input_scan.guarded_response())

    # Guard the output
    output_scan = dome.guard_output(response)
    return output_scan.guarded_response()

​

Configuration Sync

​

Framework Support

• Google ADK: register generated model callbacks with your agent
• LangGraph: scan inside graph nodes, or secure the whole graph
• Strands: attach a Dome hook provider to your agent
• LangChain: use GuardrailRunnable in your chains
• MCP servers: run a guarded proxy in front of the server
• Custom agents: wrap any LLM client with Guard calls

​

Next Steps