redpanda-data · micheleRP · May 28, 2026 · May 27, 2026 · May 28, 2026 · May 27, 2026
@@ -1,7 +1,7 @@
 name: agentic-data-plane
 title: Agentic Data Plane
 version: ~
-start_page: ROOT:index.adoc
+start_page: get-started:adp-overview.adoc
 nav:
 - modules/ROOT/nav.adoc
 asciidoc:

@@ -1,8 +1,8 @@
-* xref:ROOT:index.adoc[Overview]
-* xref:get-started:byoc-quickstart.adoc[Quickstart]
+* xref:get-started:adp-overview.adoc[Overview]
+* xref:get-started:byoc-quickstart.adoc[ADP Quickstart]
 * xref:agents:index.adoc[Agents]
 ** xref:agents:overview.adoc[Overview]
-** xref:agents:quickstart.adoc[Quickstart]
+** xref:agents:quickstart.adoc[AI Agent Quickstart]
 ** xref:agents:concepts.adoc[Concepts]
 ** xref:agents:a2a-concepts.adoc[Agent-to-Agent Concepts]
 ** xref:agents:create-agent.adoc[Create a Declarative Agent]
@@ -41,7 +41,7 @@
 *** xref:mcp:managed/zendesk.adoc[Zendesk]
 * xref:ai-gateway:index.adoc[AI Gateway]
 ** xref:ai-gateway:overview.adoc[Overview]
-** xref:ai-gateway:gateway-quickstart.adoc[Quickstart]
+** xref:ai-gateway:gateway-quickstart.adoc[AI Gateway Quickstart]
 ** xref:ai-gateway:gateway-architecture.adoc[Architecture]
 ** xref:ai-gateway:configure-provider.adoc[Configure Your LLM Provider]
 *** xref:ai-gateway:bedrock-setup.adoc[Set Up AWS Bedrock]

@@ -192,7 +192,7 @@ Enable Claude Code to discover and use tools from multiple MCP servers through a
 |Descriptive name (for example, `redpanda-data-catalog`)
 
 |Endpoint URL
-|MCP server endpoint (for example, xref:mcp/remote/overview.adoc[Remote MCP server] URL)
+|MCP server endpoint (for example, xref:integrations:remote-mcp-clients.adoc[Remote MCP server] URL)
 
 |Authentication
 |Bearer token or other authentication mechanism
@@ -467,4 +467,4 @@ Causes and solutions:
 
 == Next steps
 
-* xref:mcp/remote/overview.adoc[]
+* xref:integrations:remote-mcp-clients.adoc[]
@@ -205,7 +205,7 @@ Enable Cline to discover and use tools from multiple MCP servers through a singl
 |Descriptive name (for example, `filesystem-tools`, `code-analysis-tools`)
 
 |Endpoint URL
-|MCP server endpoint (for example, xref:mcp/remote/overview.adoc[Remote MCP server] URL)
+|MCP server endpoint (for example, xref:integrations:remote-mcp-clients.adoc[Remote MCP server] URL)
 
 |Authentication
 |Bearer token or other authentication mechanism
@@ -547,4 +547,4 @@ Causes and solutions:
 
 == Next steps
 
-* xref:mcp/remote/overview.adoc[]
+* xref:integrations:remote-mcp-clients.adoc[]
@@ -301,7 +301,7 @@ Enable Continue.dev to discover and use tools from multiple MCP servers through
 |Descriptive name (for example, `redpanda-data-catalog`, `code-search-tools`)
 
 |Endpoint URL
-|MCP server endpoint (for example, xref:mcp/remote/overview.adoc[Remote MCP server] URL)
+|MCP server endpoint (for example, xref:integrations:remote-mcp-clients.adoc[Remote MCP server] URL)
 
 |Authentication
 |Bearer token or other authentication mechanism
@@ -714,4 +714,4 @@ This is expected behavior, not a configuration issue:
 
 == Next steps
 
-* xref:mcp/remote/overview.adoc[]
+* xref:integrations:remote-mcp-clients.adoc[]
@@ -229,7 +229,7 @@ Enable Cursor to discover and use tools from multiple MCP servers through a sing
 |Descriptive name (for example, `redpanda-data-tools`, `code-search-tools`)
 
 |Endpoint URL
-|MCP server endpoint (for example, xref:mcp/remote/overview.adoc[Remote MCP server] URL)
+|MCP server endpoint (for example, xref:integrations:remote-mcp-clients.adoc[Remote MCP server] URL)
 
 |Authentication
 |Bearer token or other authentication mechanism
@@ -681,4 +681,4 @@ Causes and solutions:
 
 == Next steps
 
-* xref:mcp/remote/overview.adoc[]
+* xref:integrations:remote-mcp-clients.adoc[]
@@ -615,7 +615,7 @@ Causes and solutions:
 * **Expired token**: Generate a new API token and update the GitHub Copilot configuration
 * **Network connectivity**: Verify the cluster endpoint is accessible from the client network
 * **Provider not enabled**: Ensure at least one provider is enabled and has models in the catalog
-* **SSL/TLS issues**: Verify the cluster has valid SSL certificates
+* **TLS issues**: Verify the cluster has valid TLS certificates
 * **Organization policy blocking custom endpoints**: Check GitHub organization settings
 
 === Model not found errors

@@ -22,7 +22,7 @@ Use logs for:
 * Understanding which provider handled a request
 * Investigating latency spikes or errors for specific users
 
-Use metrics for: Aggregate analytics, trends, cost tracking across time. See xref:ai-gateway/observability-metrics.adoc[].
+Use metrics for: Aggregate analytics, trends, cost tracking across time. See xref:observability:metrics.adoc[].
 
 == Where to find logs
 
@@ -603,7 +603,7 @@ Retention period: // PLACEHOLDER: for example, 30 days, 90 days, configurable
 After retention period:
 
 * Logs are deleted automatically
-* Aggregate metrics retained longer (see xref:ai-gateway/observability-metrics.adoc[])
+* Aggregate metrics retained longer (see xref:observability:metrics.adoc[])
 
 Export logs (if needed for longer retention):
 
@@ -746,4 +746,4 @@ Note: Cost estimates are approximate. Use provider invoices for billing.
 
 == Next steps
 
-* xref:ai-gateway/observability-metrics.adoc[]
+* xref:observability:metrics.adoc[]
@@ -22,7 +22,7 @@ Use metrics for:
 * Capacity planning
 * Model/provider comparison
 
-Use logs for: Debugging specific requests, viewing full prompts/responses. See xref:ai-gateway/observability-logs.adoc[].
+Use logs for: Debugging specific requests, viewing full prompts/responses. See xref:observability:logs.adoc[].
 
 == Where to find metrics
 
@@ -855,4 +855,4 @@ Solution:
 
 == Next steps
 
-* xref:ai-gateway/observability-logs.adoc[]
+* xref:observability:logs.adoc[]
@@ -38,7 +38,7 @@ The agent card is a JSON document that describes what the agent can do and how t
 [#agent-card-location]
 === Agent card location
 
-ADP agents expose their agent cards at the `/.well-known/agent-card.json` subpath of the agent URL. You can find the agent URL on the agent overview page in the ADP UI under *Agentic AI* > *AI Agents*.
+ADP agents expose their agent cards at the `/.well-known/agent-card.json` subpath of the agent URL. You can find the agent URL on the agent overview page in the Agentic Data Plane UI under *Agentic AI* > *AI Agents*.
 
 For example, if your agent URL is `\https://my-agent.ai-agents.abc123.cloud.redpanda.com`, your agent card URL is `\https://my-agent.ai-agents.abc123.cloud.redpanda.com/.well-known/agent-card.json`.
 

@@ -79,7 +79,7 @@ Single agents are simpler to build and maintain. You have one system prompt, one
 
 However, all capabilities must coexist in one agent. Adding features increases complexity rapidly, making single agents difficult to scale to multi-domain problems.
 
-TIP: You can migrate from a single agent to a root agent with subagents without starting over. Add subagents to an existing agent using the ADP UI, then gradually move tools and responsibilities to the new subagents.
+TIP: You can migrate from a single agent to a root agent with subagents without starting over. Add subagents to an existing agent using the Agentic Data Plane UI, then gradually move tools and responsibilities to the new subagents.
 
 == Root agent with subagents pattern
 
@@ -199,7 +199,7 @@ For best results:
 
 == Model selection guide
 
-Choose models based on task complexity, latency requirements, and cost constraints. The ADP UI displays available models with descriptions when creating agents.
+Choose models based on task complexity, latency requirements, and cost constraints. The Agentic Data Plane UI displays available models with descriptions when creating agents.
 
 === Match models to task complexity
 
@@ -259,5 +259,3 @@ Provide clear error messages to users. Log errors for debugging.
 * xref:agents:integration-overview.adoc[]
 * xref:agents:a2a-concepts.adoc[]
 * xref:mcp:overview.adoc[]
-* xref:agents:overview.adoc[]
-* xref:mcp:overview.adoc[]
@@ -36,7 +36,7 @@ The two models differ in who runs the agent, who owns scaling, and how the agent
 
 |How is the agent defined?
 |It's already coded; you don't want to translate it into the declarative agent format.
-|You want a YAML / declarative definition you edit in the ADP UI.
+|You want a YAML / declarative definition you edit in the Agentic Data Plane UI.
 
 |Who scales and operates it?
 |Your team owns scaling, deploys, and the failure model.

@@ -10,7 +10,7 @@
 // TODO: Refresh screenshots against `adp-production` during Track D polish pass.
 // TODO (pre-merge verification): Confirm with team-ai whether the cloudv2 main wizard ships before GA. If it does, restructure this page to match the wizard step flow (Basics, Model, Behavior, Tools, Subagents, Review) instead of the deployed single-page form.
 
-Create a new glossterm:AI agent[] declaratively through the ADP UI. No Python or JavaScript code required. This guide walks the create form section by section, then covers the post-create steps for discovery metadata and testing.
+Create a new glossterm:AI agent[] declaratively through the Agentic Data Plane UI. No Python or JavaScript code required. This guide walks the create form section by section, then covers the post-create steps for discovery metadata and testing.
 
 After reading this page, you will be able to:
 

@@ -96,4 +96,3 @@ Monitor iteration counts during complex requests to ensure they complete within
 
 * xref:observability:concepts.adoc[]
 * xref:troubleshoot/troubleshoot-ai-agents.adoc[]
-* xref:agents:concepts.adoc[]
@@ -21,7 +21,7 @@ An AI agent is a system built around a glossterm:large language model (LLM)[] th
 
 == How agents work
 
-When you create an agent, you configure the components through the ADP UI rather than writing code:
+When you create an agent, you configure the components through the Agentic Data Plane UI rather than writing code:
 
 * *System prompt*: Defines the agent's role, responsibilities, and constraints
 * *LLM*: Interprets user intent and decides which tools to invoke

@@ -1,7 +1,7 @@
 = AI Agent Quickstart
 :page-aliases: cloud-data-platform:ai-agents:agents/quickstart.adoc
 :description: Create your first AI agent in ADP that generates and publishes event data through natural language commands.
-:page-topic-type: tutorial
+:page-topic-type: quickstart
 :personas: agent_builder
 :learning-objective-1: Create an AI agent in ADP that uses MCP tools
 :learning-objective-2: Configure the agent with a system prompt and model selection
@@ -17,11 +17,11 @@ After completing this quickstart, you will be able to:
 
 == Prerequisites
 
-* An ADP environment
+* A Redpanda Cloud BYOC environment on AWS with ADP enabled.
 
-* xref:ai-gateway:gateway-quickstart.adoc[AI Gateway configured] with at least one LLM provider enabled (OpenAI, Anthropic, Google AI, or AWS Bedrock)
+* An xref:ai-gateway:gateway-quickstart.adoc[AI Gateway] configured with at least one LLM provider (OpenAI, Anthropic, Google AI, or AWS Bedrock).
 
-* Completed the xref:mcp:create-server.adoc[Remote MCP Quickstart] to create an MCP server with the following tools deployed:
+* An MCP server created by following xref:mcp:create-server.adoc[Create an MCP Server], with the following tools deployed:
 +
 ** `generate_input`: Generates fake user event data
 ** `redpanda_output`: Publishes data to Redpanda topics
@@ -34,7 +34,7 @@ An Event Data Manager agent that:
 * Publishes events to Redpanda topics
 * Understands natural language requests like "Generate 5 login events and publish them"
 
-The agent orchestrates the `generate_input` and `redpanda_output` tools you created in the Remote MCP quickstart.
+The agent orchestrates the `generate_input` and `redpanda_output` tools you created in xref:mcp:create-server.adoc[].
 
 == Create the agent
 
@@ -87,7 +87,7 @@ Response format:
 . Select MCP tools:
 +
 * Click *Add MCP Server*
-* Select the `event-data-generator` server (created in the MCP quickstart)
+* Select the `event-data-generator` server you created in xref:mcp:create-server.adoc[]
 * Check both tools:
 ** `generate_input`
 ** `redpanda_output`
@@ -177,6 +177,7 @@ Common quickstart issue:
 
 == Next steps
 
+* xref:get-started:byoc-quickstart.adoc[ADP Quickstart]
 * xref:agents:overview.adoc[]
 * xref:agents:create-agent.adoc[]
 * xref:agents:system-prompts.adoc[]

@@ -420,5 +420,4 @@ Decision criteria enable reliable tool selection based on request context.
 == Next steps
 
 * xref:agents:quickstart.adoc[]
-* xref:agents:overview.adoc[]
 * xref:mcp:overview.adoc[]
@@ -481,6 +481,5 @@ For comprehensive guidance on monitoring agent activity, analyzing conversation
 == Next steps
 
 * xref:agents:system-prompts.adoc[]
-* xref:agents:concepts.adoc[]
 * xref:mcp:overview.adoc[]
 * xref:agents:architecture-patterns.adoc[]
@@ -267,7 +267,7 @@ Use these documented test IDs when testing the agent. If you replace the mock to
 
 == Next steps
 
-* xref:mcp:overview.adoc[Call external APIs]
+* xref:mcp:overview.adoc[]
 * xref:agents:system-prompts.adoc[]
 * xref:agents:architecture-patterns.adoc[]
 * xref:troubleshoot/troubleshoot-ai-agents.adoc[]
@@ -54,7 +54,7 @@ The infrastructure that serves the model differs based on the provider you selec
 
 . Click *Save changes*.
 
-Only enabled models will be accessible through gateways. You can enable or disable models at any time without affecting existing gateways.
+Only enabled models are accessible through gateways. You can enable or disable models at any time without affecting existing gateways.
 
 === Model naming convention
 

@@ -8,7 +8,7 @@
 
 // Source: cloudv2 `apps/aigw/docs/customer/bedrock-setup-guide.md` on origin/main, verified 2026-05-19.
 
-This guide walks you through the AWS-side setup AI Gateway needs to invoke Amazon Bedrock, then through the ADP UI flow that registers Bedrock as an LLM provider. For background on how Bedrock foundation models, cross-region inference profiles, and IAM patterns map to the provider form, see xref:ai-gateway:configure-provider.adoc#bedrock-inference-profiles[AWS Bedrock: Inference profiles and IAM] on the main provider configuration page.
+This guide walks you through the AWS-side setup AI Gateway needs to invoke Amazon Bedrock, then through the Agentic Data Plane UI flow that registers Bedrock as an LLM provider. For background on how Bedrock foundation models, cross-region inference profiles, and IAM patterns map to the provider form, see xref:ai-gateway:configure-provider.adoc#bedrock-inference-profiles[AWS Bedrock: Inference profiles and IAM] on the main provider configuration page.
 
 After completing this guide, you will be able to:
 
@@ -85,7 +85,7 @@ TIP: Don't reuse an existing IAM user. A dedicated user makes it easy to rotate
 
 == Generate access keys
 
-Generate the access keys AI Gateway will use:
+Generate the access keys AI Gateway uses:
 
 [,bash]
 ----

@@ -402,7 +402,7 @@ AI Gateway does not provide these capabilities. For current status, consult the
 * *Multi-provider routing, failover, and retries across providers.* A synthetic provider that fans requests to multiple upstreams is not part of AI Gateway.
 * *Spend limits.* Per-user, per-org, and global cost caps are not available. AI Gateway records spend and token usage for reporting in the provider *Cost & Usage* view and Governance, but it does not enforce budget caps. See xref:governance:budgets.adoc[Token budgets and limits].
 * *Rate limits.* Requests-per-second, per-minute, or per-day limits are not available.
-* *Managed MCP aggregation at the gateway.* Register MCP tool servers separately under *MCP Servers* in the ADP UI.
+* *Managed MCP aggregation at the gateway.* Register MCP tool servers separately under *MCP Servers* in the Agentic Data Plane UI.
 
 == Next steps
 

@@ -422,7 +422,7 @@ AI Gateway returns standard HTTP status codes. The upstream provider's error bod
 * Implement retry with exponential backoff for 5xx and timeout conditions.
 * Respect `Retry-After` on 429 responses.
 * Rotate service account credentials on a schedule your organization accepts.
-* Observe usage through the ADP UI on each provider's detail page.
+* Observe usage through the Agentic Data Plane UI on each provider's detail page.
 
 == Troubleshooting
 

@@ -25,15 +25,15 @@ Providers represent upstream LLM services and their associated credentials. Prov
 . Navigate to *Agentic* > *AI Gateway* > *Providers*.
 . Select a provider (for example, OpenAI, Anthropic, Google AI, AWS Bedrock).
 . On the Configuration tab, click *Add configuration* and enter the provider's credentials (API key for OpenAI, Anthropic, and Google AI; AWS access key and secret for Bedrock).
-. Verify the provider status shows "Active".
+. Verify the provider status shows as active.
 
 == Enable models
 
 After enabling a provider, enable the specific models you want to make available through your gateways.
 
 . Navigate to *Agentic* > *AI Gateway* > *Models*.
 . Enable the models you want to use (for example, `gpt-5.2-mini`, `claude-sonnet-4.5`, `claude-opus-4.6`).
-. Verify the models appear as "Enabled" in the model catalog.
+. Verify the models appear as enabled in the model catalog.
 
 TIP: Different providers have different reliability and cost characteristics. When choosing models, consider your use case requirements for quality, speed, and cost.
 
@@ -196,10 +196,10 @@ Confirm your request was routed through AI Gateway.
 
 . On the *Overview* tab, check the aggregate metrics:
 +
-* *Total Requests*: Should have incremented
-* *Total Tokens*: Shows combined input and output tokens
-* *Total Cost*: Estimated spend across all requests
-* *Avg Latency*: Average response time in milliseconds
+* Total Requests: Should have incremented.
+* Total Tokens: Shows combined input and output tokens.
+* Total Cost: Estimated spend across all requests.
+* Avg Latency: Average response time in milliseconds.
 
 . Scroll to the *Models* table to see per-model statistics:
 +
@@ -421,6 +421,7 @@ const openai = new OpenAI({
 
 == Next steps
 
+* xref:get-started:byoc-quickstart.adoc[ADP Quickstart]
 * xref:ai-gateway:aggregation.adoc[]
 * xref:integrations:index.adoc[]
 * xref:ai-gateway:gateway-architecture.adoc[]

@@ -50,11 +50,11 @@ Applications authenticate to ADP with OIDC service accounts instead of long-live
 
 === Per-provider observability
 
-The provider's detail page in the ADP UI records spend, request counts, and token counts for the last 7 days. The *Cost & Usage* tab on the *LLM Providers* page expands that view with time-series charts, provider and model grouping, date ranges, and filters for provider, model, cost type, token type, and user.
+The provider's detail page in the Agentic Data Plane UI records spend, request counts, and token counts for the last 7 days. The *Cost & Usage* tab on the *LLM Providers* page expands that view with time-series charts, provider and model grouping, date ranges, and filters for provider, model, cost type, token type, and user.
 
 == What's in the UI
 
-In the ADP UI you'll find four areas:
+In the Agentic Data Plane UI you'll find four areas:
 
 * *LLM Providers*: Create, edit, enable, and delete providers, and review provider-level cost and usage. This is the home of AI Gateway configuration.
 * *MCP Servers*: Register glossterm:MCP[] tool servers for agents. Separate from the AI Gateway proxy URL.
@@ -112,7 +112,7 @@ AI Gateway does not provide these capabilities. For current status, consult the
 * *Multi-provider routing, failover, and retries.* A synthetic provider that fans requests to multiple upstreams is not part of AI Gateway.
 * *Spend limits.* Per-user, per-org, and global cost caps are not available. AI Gateway records spend and token usage for reporting in the provider *Cost & Usage* view and Governance, but it does not enforce budget caps. See xref:governance:budgets.adoc[Token budgets and limits] for the read-only spending visibility.
 * *Rate limits.* Requests-per-second, per-minute, or per-day caps are not available.
-* *Managed MCP aggregation at the gateway.* Register MCP tool servers separately under *MCP Servers* in the ADP UI.
+* *Managed MCP aggregation at the gateway.* Register MCP tool servers separately under *MCP Servers* in the Agentic Data Plane UI.
 
 == Next steps
Original file line number	Diff line number	Diff line change
Expand Up		@@ -96,4 +96,3 @@ Monitor iteration counts during complex requests to ensure they complete within

		* xref:observability:concepts.adoc[]
		* xref:troubleshoot/troubleshoot-ai-agents.adoc[]
		* xref:agents:concepts.adoc[]