Control Hub
AI-powered agent deployment engine that transforms use cases into production-ready multi-agent systems.
Control Hub is where your AI use case becomes a production-ready application. When you click "Design App" on a use case in the Jamming Board, an Application record is created and you're redirected to Control Hub.
3 Tabs
Control Hub has three tabs: Agentic System, Test Bed, and Deploy. Test Bed and Deploy are disabled until your agents have been deployed at least once.
| Tab | Purpose |
|---|---|
| Agentic System | Design, configure, and deploy your AI agents |
| Test Bed | Live chat environment to test your deployed agentic system |
| Deploy | Generate your application code, manage API access, and move to production |
What Control Hub Does
-
Agentic System -- The AI Architect generates a multi-agent architecture using AWS Bedrock and SageMaker, with specialized agents tailored to your use case. You can review, edit, and refine agents via visual configuration or natural language chat. Approve to deploy.
-
Test Bed -- A live chat environment connected to your deployed AgentCore runtime. Test agent behavior, view real-time sub-agent orchestration in the Agent Activity Tree, and run evaluations across up to 8 metrics.
-
Deploy -- Two inner tabs: Generate App (code generation, auto-build via GitHub + Amplify, App Refiner) and API (endpoint URL, API keys, Quick Start code, Developer Guide). Business Case dialog with Cost Estimates, AWS Architecture Diagram, and Export as PDF.
-
Move to Prod -- Moves your application to production and redirects to the Application Management dashboard.