redpanda-data · micheleRP · May 29, 2026 · May 28, 2026 · May 28, 2026 · May 28, 2026
@@ -1,42 +1,43 @@
-* xref:get-started:adp-overview.adoc[Quickstarts]
+* xref:get-started:index.adoc[Get Started]
+** xref:get-started:adp-overview.adoc[Redpanda ADP Overview]
 ** xref:get-started:byoc-quickstart.adoc[ADP Quickstart]
 ** xref:get-started:gateway-quickstart.adoc[AI Gateway Quickstart]
 ** xref:get-started:quickstart.adoc[AI Agent Quickstart]
 
-* xref:connect:index.adoc[Connect data & tools]
-** xref:connect:managed/managed-catalog.adoc[Plug in any app, database, or tool]
-** xref:connect:create-agent.adoc[Turn your data source into an agent]
-** xref:connect:create-server.adoc[Build a tool server for your own data]
-** xref:connect:register-remote.adoc[Connect a tool server you host yourself]
-** xref:connect:user-delegated-oauth.adoc[Let agents act as the signed-in user]
-** xref:connect:byoa-register.adoc[Register your own agent (BYOA)]
-** xref:connect:claude-code.adoc[Claude Code]
-** xref:connect:remote-mcp-clients.adoc[Remote MCP clients]
+* xref:connect:index.adoc[Connect Data & Tools]
+** xref:connect:managed/managed-catalog.adoc[Plug in an App, Database, or Tool]
+** xref:connect:create-agent.adoc[Create an Agent]
+** xref:connect:create-server.adoc[Create an MCP Server]
+** xref:connect:register-remote.adoc[Register a Self-Managed MCP Server]
+** xref:connect:user-delegated-oauth.adoc[Configure User-Delegated OAuth]
+** xref:connect:byoa-register.adoc[Register Your Own Agent (BYOA)]
+** xref:connect:claude-code.adoc[Use Claude Code with ADP]
+** xref:connect:remote-mcp-clients.adoc[Connect Remote MCP Clients]
 
-* xref:monitor:index.adoc[Monitor & debug]
-** xref:monitor:transcripts.adoc[See what your agent did]
-** xref:monitor:troubleshoot-ai-agents.adoc[Investigate a broken run]
-** xref:monitor:metrics.adoc[Check speed, cost, and errors]
-** xref:control:guardrails/violations.adoc[Review blocked requests]
-** xref:monitor:byoa-telemetry.adoc[Send telemetry from agents you host]
+* xref:monitor:index.adoc[Monitor & Debug]
+** xref:monitor:transcripts.adoc[See What Your Agent Did]
+** xref:monitor:troubleshoot-ai-agents.adoc[Troubleshoot AI Agents]
+** xref:monitor:metrics.adoc[Check Speed, Cost, and Errors]
+** xref:control:guardrails/violations.adoc[Review Blocked Requests]
+** xref:monitor:byoa-telemetry.adoc[Send BYOA Telemetry]
 
-* xref:control:index.adoc[Control & govern]
-** xref:control:dashboard/overview.adoc[See all your agents in one place]
-** xref:control:guardrails/overview.adoc[Fix agents calling things they shouldn't]
-** xref:control:guardrails/create-guardrail.adoc[Set safety rules for all agents]
-** xref:control:budgets.adoc[Set spending limits]
-** xref:control:permissions-overview.adoc[Control who can do what]
+* xref:control:index.adoc[Control & Govern]
+** xref:control:dashboard/overview.adoc[See All Your Agents in One Place]
+** xref:control:guardrails/overview.adoc[Guardrails Overview]
+** xref:control:guardrails/create-guardrail.adoc[Create a Guardrail]
+** xref:control:budgets.adoc[Set Spend Limits]
+** xref:control:permissions-overview.adoc[Control Who Can Do What]
 
-* xref:gateway:index.adoc[Routing & LLM settings]
-** xref:gateway:overview.adoc[How the gateway works]
-** xref:gateway:configure-provider.adoc[Configure LLM provider]
-*** xref:gateway:bedrock-setup.adoc[Set up AWS Bedrock]
+* xref:gateway:index.adoc[Routing & LLM Settings]
+** xref:gateway:overview.adoc[How AI Gateway Works]
+** xref:gateway:configure-provider.adoc[Configure an LLM Provider]
+*** xref:gateway:bedrock-setup.adoc[Set Up AWS Bedrock as an LLM Provider]
 
-* xref:reference:index.adoc[Settings reference]
-** xref:control:permissions-reference.adoc[Roles and permissions matrix]
-** xref:control:guardrails/types-reference.adoc[Safety rule providers]
-** xref:reference:rpk-install.adoc[Install rpk]
-** xref:reference:rpk/index.adoc[rpk command reference]
+* xref:reference:index.adoc[Reference]
+** xref:control:permissions-reference.adoc[Roles and Permissions Reference]
+** xref:control:guardrails/types-reference.adoc[Guardrail Evaluator Types Reference]
+** xref:reference:rpk-install.adoc[Install or Update rpk]
+** xref:reference:rpk/index.adoc[rpk Command Reference]
 *** xref:reference:rpk/rpk-ai/rpk-ai.adoc[rpk ai]
 **** xref:reference:rpk/rpk-ai/rpk-ai-agent.adoc[]
 ***** xref:reference:rpk/rpk-ai/rpk-ai-agent-list.adoc[]

@@ -346,7 +346,7 @@ Common issues:
 After successful test:
 
 1. Open AI Gateway observability dashboard
-2. In the sidebar, navigate to *Agentic* > *AI Gateway* > *Gateways* > *{GATEWAY_NAME}*, then select the *Logs* tab.
+2. In the sidebar, navigate to *AI Gateway* > *Gateways* > *{GATEWAY_NAME}*, then select the *Logs* tab.
 3. Verify your test request appears
 4. Check fields:
    * Model: `openai/gpt-5.2-mini`
@@ -716,7 +716,7 @@ Causes:
 
 Solution:
 
-1. Verify model is enabled: In the sidebar, navigate to *Agentic* > *AI Gateway* > *Models* and confirm the model is enabled.
+1. Verify model is enabled: In the sidebar, navigate to *AI Gateway* > *Models* and confirm the model is enabled.
 2. Confirm format: `vendor/model_id` (for example, `openai/gpt-5.2`, not `gpt-5.2` without prefix)
 3. Check supported models: // PLACEHOLDER: link to model catalog
 

@@ -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 Agentic Data Plane 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 *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`.
 

@@ -67,7 +67,7 @@ Before you register a BYOA agent, make sure you have:
 
 * An agent running in your own infrastructure with a reachable HTTPS endpoint.
 * The ability to add an HTTPS route at `/.well-known/agent-card.json` (or equivalent) on that endpoint. See <<a2a-endpoint-contract>>.
-* The agent instrumented with OpenTelemetry, emitting the minimum required spans contract. See xref:monitor:byoa-telemetry.adoc[BYOA telemetry (OpenTelemetry)].
+* The agent instrumented with OpenTelemetry, emitting the minimum required spans contract. See xref:monitor:byoa-telemetry.adoc[BYOA telemetry].
 * The `dataplane_adp_agent_create` permission, granted by the Writer built-in role. See xref:control:permissions-reference.adoc#agent-management-permissions[Agent management permissions].
 * A name for the agent that follows DNS-1123 conventions (1–63 characters, lowercase letters / numbers / hyphens, starting with a letter). The name is immutable once the agent is registered.
 
@@ -149,7 +149,7 @@ After registering, confirm three things end-to-end:
 
 . *Discovery*: The agent appears in *AgentRegistryService.ListAgents* and in the governance dashboard's Agents list. *Type* shows as *BYOA*.
 . *A2A reachability*: A test A2A call to `https://aigw.<cluster-id>.clusters.rdpa.co/agents/<your-agent-name>/v1/message:send` returns the expected response (or a `FAILED_PRECONDITION` if your agent isn't running, but no `404 Not Found`).
-. *Telemetry*: Open the transcripts list, filter by your agent's `service.name`, and confirm a recent execution shows up with non-zero token counts and a non-empty conversation ID. If it doesn't, see xref:monitor:byoa-telemetry.adoc[BYOA telemetry (OpenTelemetry)] troubleshooting.
+. *Telemetry*: Open the transcripts list, filter by your agent's `service.name`, and confirm a recent execution shows up with non-zero token counts and a non-empty conversation ID. If it doesn't, see xref:monitor:byoa-telemetry.adoc[BYOA telemetry] troubleshooting.
 
 == Troubleshooting
 
@@ -168,7 +168,7 @@ The symptom-driven checks in this section cover the three observable parts of th
 |The agent endpoint URL on the registration record doesn't match where your agent is actually running, or the agent isn't serving `/.well-known/agent-card.json`. Update the registration with the correct URL, or fix the well-known route.
 
 |Transcripts list shows the agent column blank for your agent's runs
-|Your agent's OTel `service.name` resource attribute doesn't match the registered name (or isn't being emitted at all). See xref:monitor:byoa-telemetry.adoc[BYOA telemetry (OpenTelemetry)].
+|Your agent's OTel `service.name` resource attribute doesn't match the registered name (or isn't being emitted at all). See xref:monitor:byoa-telemetry.adoc[BYOA telemetry].
 
 |Inbound A2A calls fail with `401 Unauthorized`
 |Your agent is rejecting the access token AI Gateway presents. Confirm your agent's token validator points at the right issuer and accepts the right audience.
@@ -187,6 +187,6 @@ This page does not cover:
 == Related topics
 
 * xref:connect:a2a-concepts.adoc[Agent-to-agent concepts]
-* xref:monitor:byoa-telemetry.adoc[BYOA telemetry (OpenTelemetry)]
+* xref:monitor:byoa-telemetry.adoc[BYOA telemetry]
 * xref:connect:concepts.adoc[Agent concepts]
 * xref:connect:create-agent.adoc[Create a declarative agent]
@@ -29,7 +29,7 @@ This guide does not cover building agents that *call* Claude Code. For that, see
 
 * An Anthropic LLM provider configured in AI Gateway. If you haven't created one, follow xref:gateway:configure-provider.adoc[Configure an LLM provider] and pick *Anthropic* as the type. Enable at least one Claude model (for example, `claude-sonnet-4-6` or `claude-opus-4-7`) in the model picker.
 * Claude Code installed on the developer's workstation. See https://docs.anthropic.com/claude-code[Anthropic's Claude Code documentation].
-* A Redpanda Cloud service account with permission to invoke the provider (`dataplane_adp_llmprovider_invoke`). See xref:control:permissions-reference.adoc#llm-provider-permissions[LLM provider permissions]. Both shared-developer-tooling and per-developer setups use the same OIDC client-credentials grant; the differences are operational.
+* A Redpanda service account with permission to invoke the provider (`dataplane_adp_llmprovider_invoke`). See xref:control:permissions-reference.adoc#llm-provider-permissions[LLM provider permissions]. Both shared-developer-tooling and per-developer setups use the same OIDC client-credentials grant; the differences are operational.
 
 == Get the proxy URL
 

@@ -163,7 +163,7 @@ For multi-agent design patterns, see xref:connect:architecture-patterns.adoc[Age
 
 == Configure the service account
 
-In the *Service Account* section, set the name for the service account that authenticates the agent to other systems in the Redpanda Cloud Platform (for example, MCP servers and the Redpanda broker).
+In the *Service Account* section, set the name for the service account that authenticates the agent to other systems in Redpanda (for example, MCP servers and the Redpanda broker).
 
 . Review the auto-generated *Service Account Name*. The default uses the pattern `cluster-<cluster-id>-agent-<agent-name>-sa`.
 . Optionally, override the name. Up to 128 characters. The name cannot contain `<` or `>`.

@@ -1,3 +1,3 @@
-= Connect data & tools
+= Connect Data & Tools
 :description: Connect agents, MCP servers, and the apps and data sources behind them.
 :page-layout: index
@@ -1,4 +1,4 @@
-= Managed MCP Server Catalog
+= Plug in an App, Database, or Tool
 :description: Reference of every managed MCP server type Redpanda hosts in-process, grouped by category, with display name, description, and a link to a deep-dive where one exists.
 :page-topic-type: reference
 :personas: agent_builder, platform_engineer

@@ -1,4 +1,4 @@
-= Connect Remote MCP Clients to AI Gateway
+= Connect Remote MCP Clients
 :description: Connect external MCP clients (Claude Desktop, ChatGPT desktop, Gemini Apps) to MCP servers hosted in AI Gateway. Covers the three-piece architecture (MCP server, OAuth Provider, OAuth Client) and the two-step OAuth flow that runs end-to-end.
 :page-topic-type: how-to
 :personas: agent_builder, platform_engineer, security_compliance_lead

@@ -62,7 +62,7 @@ This granularity enables the agent to chain tools (check order status, see it's
 Create a Remote MCP server with the three tools.
 
 . Sign in to ADP.
-. Go to *Agentic AI* > *Remote MCP*.
+. Go to *Remote MCP*.
 . Click *Create MCP Server*.
 . Configure the server:
 +
@@ -113,7 +113,7 @@ The system prompt teaches the agent how to orchestrate tools. Without explicit g
 
 Create the customer support agent with the system prompt.
 
-. Go to *Agentic AI* > *AI Agents*.
+. Go to *AI Agents*.
 . Click *Create Agent*.
 . Configure the agent:
 +

@@ -46,7 +46,7 @@ Before creating agents, create the tools they'll use. You'll organize tools by d
 Account tools retrieve customer and transaction data with PII protection.
 
 . Sign in to ADP.
-. Go to *Agentic AI* > *Remote MCP*.
+. Go to *Remote MCP*.
 . Click *Create MCP Server*.
 . Configure the server:
 +
@@ -218,7 +218,7 @@ The root agent orchestrates sub-agents and makes final recommendations. You'll c
 Sub-agents inherit the LLM provider, model, resource tier, and max iterations from the root agent. This tutorial uses GPT-5 Mini and max iterations of 15 to optimize performance. Using slower models (GPT-5.2, Claude Sonnet 4.5) or high max iterations (50+) will cause sub-agents to execute slowly. Each sub-agent call could take 60-90 seconds instead of 10-15 seconds.
 ====
 
-. Go to *Agentic AI* > *AI Agents*.
+. Go to *AI Agents*.
 . Click *Create Agent*.
 . Configure the root agent:
 +
@@ -324,7 +324,7 @@ Wait for the agent status to show *Running*.
 
 Test the multi-agent system with realistic dispute scenarios. Each scenario demonstrates different patterns: clear fraud, legitimate transactions, escalation cases, and edge cases.
 
-. Go to *Agentic AI* > *AI Agents*.
+. Go to *AI Agents*.
 . Click on `dispute-resolution-agent`.
 . Open the *Inspector* tab.
 
@@ -396,7 +396,7 @@ Process disputes automatically from transaction streams. When transactions meet
 
 The pipeline needs the agent card URL to invoke the dispute resolution agent.
 
-. Go to *Agentic AI* > *AI Agents*.
+. Go to *AI Agents*.
 . Click on `dispute-resolution-agent`.
 . Open the *A2A* tab.
 . Copy the agent URL displayed at the top.
@@ -624,7 +624,7 @@ Only transactions meeting the risk threshold invoke the dispute resolution agent
 Use the pipeline metadata timestamp to find the corresponding agent execution in the *Transcripts* view.
 
 . Note the `processed_at` timestamp from the pipeline output (for example: `2026-01-26T18:30:45.000Z`).
-. Go to *Agentic AI* > *Transcripts*.
+. Go to *Transcripts*.
 . Find transcripts for `dispute-resolution-agent` that match your timestamp.
 
 [NOTE]

@@ -1,4 +1,4 @@
-= Configure User-Delegated OAuth for an MCP Server
+= Configure User-Delegated OAuth
 :description: Have each end-user authenticate against the MCP server's upstream system with their own credentials. Redpanda stores their token in the vault and injects it at call time.
 :page-topic-type: how-to
 :personas: platform_engineer, agent_builder, security_compliance_lead

@@ -86,7 +86,7 @@ Create a dedicated gateway to isolate Claude Code traffic and apply specific pol
 
 === Gateway configuration
 
-. Navigate to *Agentic* > *AI Gateway* > *Gateways*
+. Navigate to *AI Gateway* > *Gateways*
 . Click *Create Gateway*
 . Enter gateway details:
 +
@@ -153,7 +153,7 @@ Prevent runaway usage from Claude Code clients:
 
 The gateway blocks requests exceeding these limits and returns HTTP 429 errors.
 
-=== Set spending limits
+=== Set spend limits
 
 Control LLM costs:
 
@@ -452,7 +452,7 @@ Causes and solutions:
 
 * **Deferred tool loading disabled**: Enable deferred tool loading to reduce tokens by 80-90%
 * **No rate limits**: Apply per-minute rate limits to prevent runaway usage
-* **Missing spending limits**: Set monthly budget limits with blocking enforcement
+* **Missing spend limits**: Set monthly budget limits with blocking enforcement
 * **Expensive models**: Route to cost-effective models (for example, Claude Sonnet instead of Opus) for non-critical requests
 
 === Requests failing with 429 errors
@@ -463,7 +463,7 @@ Causes and solutions:
 
 * **Rate limit exceeded**: Review and increase rate limits if usage is legitimate
 * **Upstream provider rate limits**: Check if the upstream LLM provider is rate-limiting; configure failover pools
-* **Budget exhausted**: Verify monthly spending limit has not been reached
+* **Budget exhausted**: Verify monthly spend limit has not been reached
 
 == Next steps
 

@@ -97,7 +97,7 @@ Create a dedicated gateway to isolate Cline traffic and apply specific policies.
 
 === Gateway configuration
 
-. Navigate to *Agentic* > *AI Gateway* > *Gateways*
+. Navigate to *AI Gateway* > *Gateways*
 . Click *Create Gateway*
 . Enter gateway details:
 +
@@ -164,7 +164,7 @@ Cline can generate multiple requests during autonomous operations. Higher limits
 
 The gateway blocks requests exceeding these limits and returns HTTP 429 errors.
 
-=== Set spending limits
+=== Set spend limits
 
 Control LLM costs during autonomous operations:
 
@@ -520,7 +520,7 @@ Causes and solutions:
 * **Deferred tool loading disabled**: Enable deferred tool loading to reduce tokens by 80-90%
 * **Autonomous loops**: Monitor for repeated similar requests (may indicate autonomous operation stuck in a loop)
 * **No rate limits**: Apply per-minute rate limits to prevent runaway autonomous usage
-* **Missing spending limits**: Set monthly budget limits with blocking enforcement
+* **Missing spend limits**: Set monthly budget limits with blocking enforcement
 * **Expensive models for autonomous work**: Route autonomous operations to cost-effective models (for example, Claude Sonnet instead of Opus)
 * **Too many tools in context**: Reduce the number of aggregated MCP servers or enable deferred loading
 
@@ -532,7 +532,7 @@ Causes and solutions:
 
 * **Rate limit exceeded**: Review and increase rate limits if autonomous usage is legitimate
 * **Upstream provider rate limits**: Check if the upstream LLM provider is rate-limiting; configure failover pools
-* **Budget exhausted**: Verify monthly spending limit has not been reached
+* **Budget exhausted**: Verify monthly spend limit has not been reached
 * **Autonomous operation too aggressive**: Configure Cline to slow down request rate
 
 === Autonomous operations timing out