# Agentic Data Plane Learning Path > For the complete documentation index, see [llms.txt](https://docs.redpanda.com/llms.txt). Component-specific: [agentic-data-plane-full.txt](https://docs.redpanda.com/agentic-data-plane-full.txt) --- title: Agentic Data Plane Learning Path latest-operator-version: v26.2.4 latest-console-tag: v3.12.0 latest-connect-version: 4.113.1 latest-redpanda-tag: v26.2.4 docname: learning-path page-component-name: agentic-data-plane page-version: master page-component-version: master page-component-title: Agentic Data Plane page-relative-src-path: learning-path.adoc page-edit-url: https://github.com/redpanda-data/adp-docs/edit/main/modules/get-started/pages/learning-path.adoc description: Read the Agentic Data Plane docs in an order that builds from platform concepts to a running agent, governance controls, and production integration. page-topic-type: overview personas: agent_builder, platform_engineer, security_compliance_lead, pilot_lead, domain_evaluator learning-objective-1: Identify the level to start at for your role learning-objective-2: Recognize what each level lets you do when you finish it learning-objective-3: Name the page that teaches each skill page-git-created-date: "2026-09-17" page-git-modified-date: "2026-10-06" --- 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)Choose where to start | Your role | Start here | | --- | --- | | Administrator or platform engineer | Level 1: Understand the platformThe administrator quickstart in Level 2: Build and run your first agentThe access and budget pages in Level 3: Govern agents | | Agent builder | The overview and How Agents Work in Level 1: Understand the platformThe agent builder quickstart and the rest of Level 2: Build and run your first agentThe Your own agents and apps track in Level 4: Integrate with production | | Security or compliance lead | The overview and Control Who Can Do What in Level 1: Understand the platformAll of Level 3: Govern agents | | Evaluator or pilot lead | The overview in Level 1: Understand the platformSee What Your Agent Did in Level 2: Build and run your first agentAnalyze Cost and Usage in Level 3: Govern agents | ## [](#the-four-levels)The four levels | Level | When you finish it, you can | Before you start | | --- | --- | --- | | Level 1: Understand the platform | 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. | | Level 2: Build and run your first agent | 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. If your organization needs one, an administrator can create an environment. Administrators also need credentials for an LLM provider, such as the Anthropic API key the administrator quickstart uses. | | Level 3: Govern agents | 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. | | Level 4: Integrate with production | Connect your own agents, applications, and AI clients to the platform, and manage its resources as code. | Level 2, plus the parts of Level 3 your organization enforces. | ## [](#level-1)Level 1: Understand the platform Five short conceptual pages. Read them in order. 1. [Redpanda Agentic Data Plane Overview](https://docs.redpanda.com/agentic-data-plane/get-started/adp-overview/) 2. [How AI Gateway Works](https://docs.redpanda.com/agentic-data-plane/gateway/overview/) 3. [How MCP Servers Work](https://docs.redpanda.com/agentic-data-plane/connect/mcp-overview/) 4. [How Agents Work](https://docs.redpanda.com/agentic-data-plane/connect/agents-overview/) 5. [Control Who Can Do What](https://docs.redpanda.com/agentic-data-plane/control/permissions-overview/) ## [](#level-2)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 | Quickstart for Administrators, unless a provider already existsQuickstart for Agent Builders | | Agents | Understand Agent ConceptsSee What Your Agent Did | | MCP servers | Plug in an App, Database, or ToolCreate an MCP ServerCode ModeTest an MCP Server’s Tools with the Inspector | ## [](#level-3)Level 3: Govern agents The controls are independent. Take the topics in the order your organization enforces them. | Topic | Read | | --- | --- | | Access and tool data | Manage Access PoliciesRoles and Permissions ReferenceShape Tool Data with Data Policies | | Guardrails | How Guardrails WorkCreate a GuardrailReview Blocked Requests | | Spend | Set Up BudgetsAnalyze Cost and UsageTrack Spend by TagLimits and Defaults | | Audit and monitoring | Review the Audit LogMonitor Agent ActivityTroubleshoot Agents | ## [](#level-4)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 Effective System PromptsChoose an Agent ArchitectureConnect Your App to AI GatewayRun Claude Code and Codex through AI GatewaySet Up a Self-Managed Agent, with Self-Managed Agent Telemetry ReferenceHow Observability Works | 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 | Connect Agents with A2AChoose an Integration PatternTrigger Agents, then Connect an Agent to Microsoft Teams or Run an Agent on a Schedule | Invoke an agent from another agent or an application over the agent-to-agent (A2A) protocol, and start an agent from Microsoft Teams or on a schedule. | | Authentication and external clients | Configure an OAuth ProviderConfigure User-Delegated OAuthSet Up GitHub OAuth Provider and MCP ServerRegister a Self-Managed MCP ServerConnect Remote MCP ClientsUse an MCP Server from an AI Client | 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 | Use the Agentic Data Plane CLIManage Resources with GitOps | Manage providers, servers, agents, and policies from the CLI and keep them in version control. | ## [](#keep-up-with-changes)Keep up with changes The product changes often. Read the [Release Notes](https://docs.redpanda.com/agentic-data-plane/reference/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. ## [](#next-steps)Next steps - [Redpanda Agentic Data Plane Overview](https://docs.redpanda.com/agentic-data-plane/get-started/adp-overview/) - [Quickstart for Agent Builders](https://docs.redpanda.com/agentic-data-plane/get-started/agent-builder-quickstart/) - [Quickstart for Administrators](https://docs.redpanda.com/agentic-data-plane/get-started/adp-quickstart/)