redpanda-data · micheleRP · Feb 4, 2026 · Feb 3, 2026 · Feb 3, 2026 · Feb 3, 2026
@@ -0,0 +1,6 @@
+=== Agent2Agent (A2A) protocol
+:term-name: Agent2Agent (A2A) protocol
+:hover-text: Communication protocol that enables AI agents to discover, coordinate with, and delegate tasks to other agents in a distributed system.
+:category: Agentic Data Plane
+
+The A2A protocol allows agents to work together by sharing capabilities, coordinating workflows, and distributing complex tasks across multiple specialized agents. It provides standardized messaging, capability discovery, and task delegation mechanisms for multi-agent systems.
@@ -0,0 +1,6 @@
+=== Agentic Data Plane (ADP)
+:term-name: Agentic Data Plane (ADP)
+:hover-text: Infrastructure layer that enables AI agents to discover, connect to, and interact with data sources and tools through standardized protocols.
+:category: Agentic Data Plane
+
+The Agentic Data Plane provides the underlying infrastructure for AI agents to access streaming data, invoke tools, and coordinate operations across distributed systems using protocols like MCP and A2A.
@@ -0,0 +1,6 @@
+=== AI agent
+:term-name: AI agent
+:hover-text: An autonomous program that uses AI models to interpret requests, make decisions, and interact with tools and data sources.
+:category: Agentic Data Plane
+
+AI agents can understand natural language instructions, reason about tasks, invoke tools through MCP servers, and coordinate multiple operations to accomplish complex workflows.
@@ -0,0 +1,6 @@
+=== AI token
+:term-name: AI token
+:hover-text: A credential used specifically for authenticating AI agents and authorizing their access to resources in agentic systems.
+:category: Agentic Data Plane
+
+AI tokens are specialized authentication credentials for AI agents, distinct from bearer tokens used in traditional API authentication. They enable agents to authenticate with MCP servers and access data plane resources while maintaining audit trails of agent operations.
@@ -1,6 +1,6 @@
 === authentication
 :term-name: authentication
-:hover-text: The process of verifying the identity of a principal, user, or service account. 
+:hover-text: The process of verifying the identity of a principal, user, or service account. Also known as AuthN.
 :category: Redpanda security
 
 ifndef::env-cloud[]

@@ -1,6 +1,6 @@
 === authorization
 :term-name: authorization
-:hover-text: The process of specifying access rights to resources. Access rights are enforced through roles or access-control lists (ACLs).
+:hover-text: The process of specifying access rights to resources. Access rights are enforced through roles or access control lists (ACLs). Also known as AuthZ.
 :category: Redpanda security
 
 ifndef::env-cloud[]

@@ -0,0 +1,6 @@
+=== context window
+:term-name: context window
+:hover-text: The maximum amount of text (measured in tokens) that an LLM can process in a single request.
+:category: Agentic Data Plane
+
+The context window determines how much information an agent can consider at once, including the system prompt, conversation history, tool outputs, and retrieved documents. Larger context windows enable more sophisticated reasoning but may increase latency and cost. Common sizes range from 8K to 200K+ tokens.
@@ -0,0 +1,6 @@
+=== frontier model
+:term-name: frontier model
+:hover-text: The most advanced and capable AI models available, representing the current state-of-the-art in language understanding and reasoning.
+:category: Agentic Data Plane
+
+Frontier models are cutting-edge large language models with exceptional reasoning, planning, and problem-solving capabilities. Examples include GPT-4, Claude 3, and Gemini Ultra. These models are commonly used to power sophisticated AI agents that require advanced decision-making and tool orchestration.
@@ -0,0 +1,6 @@
+=== identity provider (IdP)
+:term-name: identity provider (IdP)
+:hover-text: A service that creates, maintains, and manages identity information while providing authentication services to applications.
+:category: Redpanda security
+
+Identity providers authenticate users and issue tokens that applications can use to verify identity and access permissions. Common IdPs include Okta, Auth0, Azure AD, and Google Identity Platform.
@@ -1,4 +1,4 @@
-=== Kakfa API
-:term-name: Kakfa API
+=== Kafka API
+:term-name: Kafka API
 :hover-text: Producers and consumers interact with Redpanda using the Kafka API. It uses the default port 9092.
 :category: Redpanda core
@@ -0,0 +1,6 @@
+=== large language model (LLM)
+:term-name: large language model (LLM)
+:hover-text: An AI model trained on vast amounts of text data that can understand and generate human-like text, reason about tasks, and follow instructions.
+:category: Agentic Data Plane
+
+Large language models power AI agents by providing natural language understanding, reasoning capabilities, and the ability to plan and execute complex tasks. LLMs interpret user requests, decide which tools to invoke, and synthesize responses based on retrieved data.
@@ -0,0 +1,6 @@
+=== MCP client
+:term-name: MCP client
+:hover-text: An AI application or agent that connects to MCP servers to discover and invoke tools.
+:category: Agentic Data Plane
+
+MCP clients use the Model Context Protocol to communicate with MCP servers, discovering available tools, understanding their capabilities, and invoking them with appropriate parameters. The client handles authentication, request formatting, and response processing.
@@ -0,0 +1,6 @@
+=== MCP server
+:term-name: MCP server
+:hover-text: A service that exposes tools and resources using the Model Context Protocol, allowing AI agents to discover and invoke them.
+:category: Agentic Data Plane
+
+MCP servers act as bridges between AI agents and external systems, providing standardized interfaces for tool discovery, invocation, and resource access.
@@ -0,0 +1,6 @@
+=== Model Context Protocol (MCP)
+:term-name: MCP
+:hover-text: A standardized protocol that enables AI agents to connect with external data sources and tools in Redpanda.
+:category: Agentic Data Plane
+
+MCP provides a consistent interface for AI applications to discover and interact with data sources, services, and computational tools through Redpanda infrastructure.
@@ -0,0 +1,6 @@
+=== observability (o11y)
+:term-name: observability (o11y)
+:hover-text: The ability to understand a system's internal state by examining its external outputs, such as traces, metrics, and logs.
+:category: Agentic Data Plane
+
+In Redpanda's agentic systems, observability enables debugging agent behavior, monitoring performance, analyzing execution flow, and identifying bottlenecks through transcripts captured in the `redpanda.otel_traces` topic.
@@ -0,0 +1,6 @@
+=== OpenID Connect (OIDC)
+:term-name: OpenID Connect (OIDC)
+:hover-text: Authentication layer built on OAuth 2.0 that allows clients to verify user identity and obtain basic profile information.
+:category: Redpanda security
+
+OpenID Connect provides a standardized way for applications to authenticate users through identity providers. In Redpanda's agentic systems, OIDC enables secure authentication for AI agents and MCP servers accessing cloud resources.
@@ -0,0 +1,6 @@
+=== OpenTelemetry
+:term-name: OpenTelemetry
+:hover-text: Open-source observability framework that provides standardized APIs, libraries, and tools for capturing and exporting telemetry data.
+:category: Agentic Data Plane
+
+OpenTelemetry provides standardized APIs for capturing traces, metrics, and logs from applications. Redpanda agents and MCP servers automatically emit OpenTelemetry traces to the `redpanda.otel_traces` topic to provide complete observability into agentic system operations.
@@ -0,0 +1,6 @@
+=== OTLP (OpenTelemetry Protocol)
+:term-name: OTLP
+:hover-text: Standard protocol for encoding and transmitting telemetry data defined by the OpenTelemetry project.
+:category: Agentic Data Plane
+
+OTLP is the OpenTelemetry Protocol specification for encoding and transmitting telemetry data. Redpanda stores spans in the `redpanda.otel_traces` topic using a Protobuf schema that closely follows the OTLP specification.
@@ -0,0 +1,6 @@
+=== processor
+:term-name: processor
+:hover-text: A Redpanda Connect component that transforms data, validates inputs, or calls external APIs within a processing pipeline.
+:category: Redpanda Connect
+
+Processors are stateless components in Redpanda Connect that operate on individual messages or batches. When used as MCP tools, processors handle data transformations, validate parameters, and invoke external services. Each processor executes independently per request with no state maintained between invocations.
@@ -0,0 +1,6 @@
+=== prompt
+:term-name: prompt
+:hover-text: Natural language instructions or context provided to an LLM to guide its behavior and responses.
+:category: Agentic Data Plane
+
+Prompts are the primary way to communicate with LLMs and AI agents. They can include instructions, examples, context, and questions that guide the model's reasoning and output. Effective prompt design is critical for agent performance and reliability.
@@ -0,0 +1,6 @@
+=== span
+:term-name: span
+:hover-text: A single unit of work within a trace representing one operation, such as a data processing operation or an external API call.
+:category: Agentic Data Plane
+
+Spans are organized in the Redpanda UI as parent-child relationships that show how operations flow through the system. Each span captures details about a specific operation, including timing, status, and metadata.
@@ -0,0 +1,6 @@
+=== subagent
+:term-name: subagent
+:hover-text: A specialized AI agent that handles specific tasks or domains as part of a larger multi-agent system.
+:category: Agentic Data Plane
+
+Subagents are autonomous components within a multi-agent architecture that have focused expertise in particular domains or operations. They communicate with a parent agent or other subagents to accomplish complex workflows that require coordination across multiple specializations.
@@ -0,0 +1,6 @@
+=== system prompt
+:term-name: system prompt
+:hover-text: Initial instructions that define an agent's role, capabilities, and behavioral guidelines.
+:category: Agentic Data Plane
+
+The system prompt is provided at the start of an agent session and establishes the agent's identity, available tools, operating constraints, and response style. It remains active throughout the conversation and shapes all subsequent agent behavior and decision-making.
@@ -0,0 +1,6 @@
+=== tool invocation
+:term-name: tool invocation
+:hover-text: The process of an AI agent executing an MCP tool to perform a specific operation.
+:category: Agentic Data Plane
+
+Tool invocation occurs when an agent determines that it needs to use a tool, formats the request with appropriate parameters, sends it to the MCP server, and processes the response. Each invocation is captured in transcripts as spans for observability and debugging.
@@ -0,0 +1,6 @@
+=== trace
+:term-name: trace
+:hover-text: The complete lifecycle of a request captured as a collection of spans, showing how operations relate to each other.
+:category: Agentic Data Plane
+
+A trace represents the complete lifecycle of a request (for example, a tool invocation from start to finish). A trace contains one or more spans organized hierarchically, showing how operations relate to each other.
@@ -0,0 +1,6 @@
+=== transcript
+:term-name: transcript
+:hover-text: Complete observability record of agent or MCP server operations captured as OpenTelemetry traces and stored in the redpanda.otel_traces topic.
+:category: Agentic Data Plane
+
+Transcripts capture tool invocations, agent reasoning steps, data processing operations, external API calls, error conditions, and performance metrics. They provide a complete record of how agentic systems operate, enabling debugging, auditing, and performance analysis.