Build in Console

Create, test, and iterate on agents visually in Console, then run them from your code with the API.

Console provides a visual interface for creating and configuring agents. It lets you iterate on configuration interactively before writing code.

Managed Agents API requests require the managed-agents-2026-04-01 beta header, except memory store endpoints, which use agent-memory-2026-07-22 instead. The SDK sets the correct beta header automatically. See Beta headers.

How to build an agent

The visual interface walks you through each field of an agent definition:

• Model and system prompt: Pick a model and write the system prompt in a full-width editor.
• MCP servers: Add remote MCP servers by URL and authenticate your agent to take action on your behalf.
• Tools: Extend your agent’s capabilities using a pre-built agent toolset and MCP tools.
• Skills: Attach OMA or custom skills from your organization’s library.

As you configure, Console shows the equivalent API request so you can copy it into your code once you’re satisfied.

Testing an agent

Console includes an inline session runner. After configuring your agent, you can start a test session directly, send messages, and watch the event stream without leaving the page. This is the fastest way to check that your system prompt and tool selection produce the behavior you expect.

From Console to your codebase

Once your agent works as expected:

1. Copy the agent ID and environment ID from Console.
2. Reference them in your code when creating sessions:

cURL

session=$(curl -fsSL http://localhost:38080/v1/sessions \
  -H "x-api-key: $OMA_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "anthropic-beta: managed-agents-2026-04-01" \
  -H "content-type: application/json" \
  -d '{
    "agent": "agent_01J8XkN5uT3vHpLqRfWdY2",
    "environment_id": "env_01K2mPsT7hNwR4jXuLvCqD8",
    "title": "My first session"
  }')