Deploy a Template-Based Agent

This guide shows you how to deploy an Agent resource using an operator-managed template image, configure its tools and sub-agents, and verify it is running.

Prerequisites

Create the Agent

Apply an Agent resource with spec.framework set and no spec.image. The operator resolves the container image from its built-in template registry.

The example below deploys a news agent that calls two tool servers and delegates to a summarizer sub-agent:

apiVersion: runtime.agentic-layer.ai/v1alpha1
kind: Agent
metadata:
  name: news-agent
spec:
  framework: google-adk
  description: "A news agent that fetches and summarizes current articles"
  instruction: "You are a news agent that can fetch current news articles and provide summaries. Use the news fetcher tool to get articles and provide concise summaries."
  model: "gemini/gemini-2.5-flash"

  # External tools the agent can use
  tools:
    # Reference to ToolServer in the same namespace
    - name: news_fetcher
      upstream:
        toolServerRef:
          name: news_fetcher_toolserver

    # Direct URL to external MCP server
    - name: web_fetcher
      upstream:
        external:
          url: "https://mcp.example.com/web-fetch"

  # Sub-agents this agent can delegate to
  subAgents:
    - name: summarizer_agent
      url: "https://agents.example.com/summarizer-agent.json"
      interactionType: "tool_call"

  protocols:
    - type: A2A
  replicas: 1
  env:
    - name: GEMINI_API_KEY
      value: "your-gemini-api-key-here"
kubectl apply -f news-agent.yaml

Verify

# Check the Agent resource status
kubectl get agent news-agent

# Check the underlying Deployment
kubectl get deployment news-agent

# View agent logs
kubectl logs -l app=news-agent

The agent is ready when the Deployment reports all replicas available.

Related