Agentic Data Plane Learning Path
The Agentic Data Plane docs are grouped by task. This page puts them in learning order: four levels, each with what you can do when you finish it, so you can skip what you already know.
After reading this page, you will be able to:
-
Identify the level to start at for your role
-
Recognize what each level lets you do when you finish it
-
Name the page that teaches each skill
Choose where to start
| Your role | Start here |
|---|---|
Administrator or platform engineer |
|
Agent builder |
|
Security or compliance lead |
|
Evaluator or pilot lead |
|
The four levels
| Level | When you finish it, you can | Before you start |
|---|---|---|
Name the components and who runs each, explain how the platform gives an agent an identity, mediates its calls, and records what it did, and tell a managed agent or MCP server from a self-managed one. |
Nothing. Start here if you have never used the product. |
|
Configure a LLM provider, create and test an MCP server, build an agent and test it in the Playground, and read its transcript. |
Level 1 and access to an Agentic Data Plane environment. Administrators also need credentials for an LLM provider, such as the Anthropic API key the administrator quickstart uses. |
|
Decide who can invoke which agent or tool, block or mask content with guardrails, cap and trace spend, shape what tools return, and read the audit log. |
Level 2 and a running agent to govern. |
|
Connect your own agents, applications, pipelines, and AI clients to the platform, and manage its resources as code. |
Level 2, plus the parts of Level 3 your organization enforces. |
Level 2: Build and run your first agent
Start with the quickstart for your role, then read about the pieces it used.
| Topic | Read |
|---|---|
Quickstarts |
|
Agents |
|
MCP servers |
Level 3: Govern agents
The controls are independent. Take the topics in the order your organization enforces them.
| Topic | Read |
|---|---|
Access and tool data |
|
Guardrails |
|
Spend |
|
Audit and monitoring |
Level 4: Integrate with production
Four tracks. Take the ones your project needs.
| Track | Read | When you finish it, you can |
|---|---|---|
Your own agents and apps |
Write a system prompt that holds up under real traffic, choose an agent architecture, point your own application or coding assistant at the gateway, and register an agent you run yourself so it shows up in transcripts. |
|
Agents in your systems |
Invoke an agent from another agent or a Redpanda pipeline over the agent-to-agent (A2A) protocol, and start an agent from Microsoft Teams or on a schedule. |
|
Authentication and external clients |
Let each user reach an upstream system with their own credentials, register an OAuth provider, bring your own MCP server under the gateway, and connect chat apps and IDEs to your servers. |
|
Resources as code |
Manage providers, servers, agents, and policies from the CLI and keep them in version control. |
Keep up with changes
The product changes often. Read the Release Notes for each version and reread the pages for the product areas you use. A Preview badge marks a feature whose details can still move. Pages without a badge describe generally available (GA) behavior.
