Agentic Data Plane

How Agents Work

Redpanda Agentic Data Plane AI agents take a declarative approach: instead of writing Python or JavaScript agent code, you declare the behavior you want by selecting an LLM, writing a system prompt, and attaching prebuilt tools and integrations. Agentic Data Plane runs the agent for you and handles execution and tool orchestration.

After reading this page, you will be able to:

  • Describe what AI agents are and their essential components

  • Explain how agents reach tools and live data through MCP servers

  • Identify use cases where Agentic Data Plane agents provide value

What is an AI agent?

An AI agent is a system built around a large language model (LLM) that interprets user intent, selects the right tools, and chains multiple steps into a workflow. In Agentic Data Plane, agents are declarative: you configure the agent’s role, constraints, and available tools rather than writing imperative agent code. Agents reach tools through MCP servers.

Declarative agent components

When you create an agent, you configure the components through Agentic Data Plane rather than writing code:

  • System prompt: Defines the agent’s role, responsibilities, and constraints

  • LLM: Interprets user intent and decides which tools to invoke

  • Tools: External capabilities exposed through the Model Context Protocol (MCP)

  • Subagents: Optional delegates, each with its own instructions and tools, that the agent hands focused tasks to

  • Context: Conversation history and tool results

An agent sees live data only through its tools or through the messages it receives.

Beyond these components, an agent can be started by triggers, such as a Microsoft Teams chat or a schedule, and it publishes an agent card that other agent-to-agent (A2A) clients use to discover it.

If you run an agent on your own infrastructure, you can register it as a self-managed agent so it appears alongside managed ones.

When a user makes a request, the LLM receives the system prompt and context, decides which tools to invoke, and processes the results. This cycle repeats until the task completes.

For a deeper understanding of how agents execute, manage context, and maintain state, see Understand Agent Concepts.

Key benefits

Agentic Data Plane agents are designed to reduce the infrastructure and integration work of building production AI systems.

  • Declarative configuration: Configure agent behavior instead of coding it, with access to a broad library of prebuilt tools and integrations for data sources, APIs, and services.

  • Live data through tools: Agents read current business state through MCP servers instead of batch snapshots.

  • Managed and self-managed MCP servers: Standardized tool access across any MCP-compatible server.

  • Managed infrastructure: Deployment and security handled for you.

  • Integrated secrets management: API keys and credentials stored securely.

Use cases

Agentic Data Plane AI agents unlock new capabilities across multiple fields.

For AI agent developers

Build agents grounded in real-time data instead of static snapshots. Connect your agent to live order status, inventory levels, and customer history so responses reflect current business state, not stale training data.

For application developers

Add conversational AI to existing applications without rebuilding your backend. Expose your services as MCP tools and let agents orchestrate complex multi-step workflows through natural language.

Limitations

  • Agents can use only MCP servers that are created or registered in Agentic Data Plane, either managed servers or self-managed servers you register.

  • Cross-agent calling between separate agents is not supported. Use internal subagents for delegation within a single agent.

Next steps