Cloudera Docs

Key Features of Agent Studio

Learn the key features of Agent Studio and how they empower users to build and manage intelligent agents effectively.

  • Design Agentic Workflows with a Low-Code Interface: Agent Studio leverages workflows as the foundational structure for AI agents. A workflow represents a network of collaborative agents working together to perform a sequence of interconnected tasks. With the low-code interface, you can easily:
    • Create agents and assign them specific tasks and tools.
    • Define agentic workflows as either conversational or task-oriented.
    • Assign a manager agent to oversee and coordinate interactions between agents.
  • Pre-Built and Custom Workflow Templates: Agent Studio includes a comprehensive library of pre-built workflows and tools to expedite development. Additionally, you can also create custom workflows and tools, which can be saved and managed as reusable templates for team-wide use.
  • Agent and Task Configuration: Agents are intelligent entities capable of decision-making, executing actions, and collaboration. With Agent Studio, you can:
    • Define each agent's role, goal, and contextual backstory.
    • Assign specific tasks and tools to individual agents.
    • Use AI-assisted authoring to generate agents using natural language input.
  • Development and Extension of Custom Tools: Tools allow agents to interact with external systems, such as APIs, databases, or business logic, beyond the scope of LLMs. Agent Studio supports:
    • Use of built-in tools or development of custom tools.
    • Extension of existing tools by modifying logic, parameters, or API integrations.
    • Development of new tools from scratch using Cloudera AI Workbench notebooks and Python sessions.
  • Integration with AI Models: Easily integrate your workflow with the LLM of your choice by registering a model and providing API key information. You can connect to Cloudera AI Inferencing or use any OpenAI-compatible model provider.
  • Test and Debug Workflows: Ensure workflow quality and correctness through comprehensive testing and debugging features:
    • Execute workflows with test inputs and visualize their execution using interactive flow diagrams.
    • Access step-by-step logs and animations in real-time.
    • Use playback mode to analyze and debug specific workflow steps.
  • Deploy Workflows as Endpoints and Applications: Once a workflow is finalized, workflow can be deployed for production use. Deployment capabilities include
    • Automatic generation of a Workbench Model endpoint.
    • Creation of a default user-facing application for interaction with the workflow.
  • Monitor Workflow Performance: Agent Studio integrates with Phoenix, an open-source observability tool, to provide:
    • Real-time monitoring of latency, token usage, inputs, outputs, and execution traces.
    • Access to a dedicated observability panel within the Workflow UI and Phoenix dashboards in the Clouder AI Workbench.
  • User-Facing Applications and Custom UI Development: Each deployed workflow includes a default front-end interface for users. To further customize the experience, build your own applications using Agent Studio’s Python SDK and APIs.