diff --git a/modules/ROOT/pages/index.adoc b/modules/ROOT/pages/index.adoc index ac60c01..faa4474 100644 --- a/modules/ROOT/pages/index.adoc +++ b/modules/ROOT/pages/index.adoc @@ -36,9 +36,9 @@ For more information, see xref:agents:overview.adoc[]. glossterm:MCP server[,MCP servers] translate agent intent into connections to databases, queues, HRIS, CRMs, and other business systems. They are the simplest way to give agents context and capabilities without writing glue code. -Under the hood, MCP servers wrap the same proven connectors that power some of the world's largest e-commerce, EV, electricity, and AI companies. Built on xref:redpanda-cloud:develop:connect/about.adoc[Redpanda Connect], they are lightweight, support OIDC-based authentication, and enforce deterministic policies at the tool level. You define tools in YAML, and policy enforcement programmatically prevents prompt injection, SQL injection, and other agent-based attacks. +MCP servers are lightweight, support OIDC-based authentication, and enforce deterministic policies at the tool level. You define tools in YAML, and policy enforcement programmatically prevents prompt injection, SQL injection, and other agent-based attacks. -With over 300 connectors and real-time debugging capabilities, you reduce integration time while getting enterprise-grade security. You can reuse your existing infrastructure and data sources rather than building new integrations from scratch. +With real-time debugging capabilities, you reduce integration time while getting enterprise-grade security. You can reuse your existing infrastructure and data sources rather than building new integrations from scratch. For more information, see xref:mcp:overview.adoc[MCP Servers Overview]. diff --git a/modules/ROOT/partials/ai-hub-mode-indicator.adoc b/modules/ROOT/partials/ai-hub-mode-indicator.adoc index 6ad7d9b..8200054 100644 --- a/modules/ROOT/partials/ai-hub-mode-indicator.adoc +++ b/modules/ROOT/partials/ai-hub-mode-indicator.adoc @@ -1,8 +1,8 @@ [tabs] ==== -Redpanda Cloud Console:: +ADP UI:: + -In the Redpanda Cloud Console: +In ADP: + . Navigate to *Agentic* → *AI Gateway* → *Gateways*. . Select a gateway from your list. diff --git a/modules/ROOT/partials/ai-hub/configure-ai-hub.adoc b/modules/ROOT/partials/ai-hub/configure-ai-hub.adoc index 2eb77ce..40a77f2 100644 --- a/modules/ROOT/partials/ai-hub/configure-ai-hub.adoc +++ b/modules/ROOT/partials/ai-hub/configure-ai-hub.adoc @@ -18,17 +18,17 @@ After reading this page, you will be able to: == Prerequisites -* Access to the Redpanda Cloud Console with administrator privileges +* Access to ADP with administrator privileges * API keys for at least one LLM provider: ** OpenAI: API key from https://platform.openai.com/api-keys ** Anthropic: API key from https://console.anthropic.com/settings/keys -* A Redpanda Cloud workspace +* An ADP workspace == Create an AI Hub gateway Creating an AI Hub gateway is significantly simpler than creating a Custom mode gateway because all routing rules and backend pools are pre-configured. -. In the Redpanda Cloud Console, navigate to *Agentic* → *AI Gateway* → *Gateways*. +. In ADP, navigate to *Agentic* → *AI Gateway* → *Gateways*. . Click *Create Gateway*. . Select *AI Hub* as the gateway mode. . Configure basic settings: diff --git a/modules/ROOT/partials/ai-hub/use-ai-hub-gateway.adoc b/modules/ROOT/partials/ai-hub/use-ai-hub-gateway.adoc index 9aec958..ab1b3e7 100644 --- a/modules/ROOT/partials/ai-hub/use-ai-hub-gateway.adoc +++ b/modules/ROOT/partials/ai-hub/use-ai-hub-gateway.adoc @@ -19,7 +19,7 @@ After reading this page, you will be able to: == Before you begin * You have access to at least one AI Hub gateway (provided by your administrator) -* You have a Redpanda Cloud API key +* You have an ADP API key * You have Python 3.8+ or Node.js 18+ installed (for code examples) == Identify an AI Hub gateway diff --git a/modules/ROOT/partials/integrations/claude-code-admin.adoc b/modules/ROOT/partials/integrations/claude-code-admin.adoc index 566da41..799e767 100644 --- a/modules/ROOT/partials/integrations/claude-code-admin.adoc +++ b/modules/ROOT/partials/integrations/claude-code-admin.adoc @@ -44,7 +44,7 @@ Claude Code requires access to LLM providers through the gateway. Enable at leas Claude Code uses Anthropic models by default. To enable Anthropic: -. Navigate to *AI Gateway* > *Providers* in the Redpanda Cloud console +. Navigate to *AI Gateway* > *Providers* in ADP . Select *Anthropic* from the provider list . Click *Add configuration* . Enter your Anthropic API key @@ -268,7 +268,7 @@ Claude Code clients authenticate using bearer tokens. === Generate API tokens -. Navigate to *Security* > *API Tokens* in the Redpanda Cloud console +. Navigate to *Security* > *API Tokens* in ADP . Click *Create Token* . Enter token details: + diff --git a/modules/ROOT/partials/integrations/claude-code-user.adoc b/modules/ROOT/partials/integrations/claude-code-user.adoc index 450f589..804794c 100644 --- a/modules/ROOT/partials/integrations/claude-code-user.adoc +++ b/modules/ROOT/partials/integrations/claude-code-user.adoc @@ -202,7 +202,7 @@ If deferred tool loading is enabled in your gateway, you'll see a search tool an Check that requests route through the gateway by monitoring the AI Gateway dashboard: -. Open the Redpanda Cloud Console +. Sign in to ADP . Navigate to your gateway's observability dashboard . Send a test request from Claude Code: + @@ -292,7 +292,7 @@ curl -H "Authorization: Bearer YOUR_API_KEY" \ /mcp ---- + -You should receive a valid MCP protocol response. If you get `401 Unauthorized`, regenerate your API key in the Redpanda Cloud Console. +You should receive a valid MCP protocol response. If you get `401 Unauthorized`, regenerate your API key in ADP. . **Gateway endpoint URL mismatch** + @@ -335,7 +335,7 @@ Ensure requests use the `vendor/model_id` format (for example, `anthropic/claude . **Gateway geographic distance** + -If your gateway is in a different region than you or the upstream provider, this adds network latency. Check gateway region in the Redpanda Cloud Console. +If your gateway is in a different region than you or the upstream provider, this adds network latency. Check gateway region in ADP. . **Provider pool failover** + diff --git a/modules/ROOT/partials/integrations/cline-admin.adoc b/modules/ROOT/partials/integrations/cline-admin.adoc index 856dd29..469286f 100644 --- a/modules/ROOT/partials/integrations/cline-admin.adoc +++ b/modules/ROOT/partials/integrations/cline-admin.adoc @@ -55,7 +55,7 @@ Cline requires access to LLM providers through the gateway. Enable at least one Cline uses Anthropic models by default. To enable Anthropic: -. Navigate to *AI Gateway* > *Providers* in the Redpanda Cloud console +. Navigate to *AI Gateway* > *Providers* in ADP . Select *Anthropic* from the provider list . Click *Add configuration* . Enter your Anthropic API key @@ -286,7 +286,7 @@ Cline clients authenticate using bearer tokens. === Generate API tokens -. Navigate to *Security* > *API Tokens* in the Redpanda Cloud console +. Navigate to *Security* > *API Tokens* in ADP . Click *Create Token* . Enter token details: + diff --git a/modules/ROOT/partials/integrations/cline-user.adoc b/modules/ROOT/partials/integrations/cline-user.adoc index 05a67c1..a337b7b 100644 --- a/modules/ROOT/partials/integrations/cline-user.adoc +++ b/modules/ROOT/partials/integrations/cline-user.adoc @@ -246,7 +246,7 @@ Send a test message in the Cline chat panel: Then verify in the AI Gateway dashboard: -. Open the Redpanda Cloud Console +. Sign in to ADP . Navigate to your gateway's observability dashboard . Filter by gateway ID . Verify: @@ -466,7 +466,7 @@ curl -H "Authorization: Bearer YOUR_API_KEY" \ /v1/models ---- + -You should receive a list of available models. If you get `401 Unauthorized`, regenerate your API key in the Redpanda Cloud Console. +You should receive a list of available models. If you get `401 Unauthorized`, regenerate your API key in ADP. . **Gateway endpoint URL mismatch** + @@ -715,7 +715,7 @@ This loads only essential tools initially. Cline queries for additional tools on Use AI Gateway spend limits to prevent runaway costs: -. Navigate to your gateway in the Redpanda Cloud Console +. Navigate to your gateway in ADP . Set monthly spend limit (for example, $500/month) . Configure alerts before reaching limit diff --git a/modules/ROOT/partials/integrations/continue-admin.adoc b/modules/ROOT/partials/integrations/continue-admin.adoc index 429a4b7..441ff31 100644 --- a/modules/ROOT/partials/integrations/continue-admin.adoc +++ b/modules/ROOT/partials/integrations/continue-admin.adoc @@ -58,7 +58,7 @@ Continue.dev works with multiple providers. Enable the providers your users will To enable Anthropic with native format support: -. Navigate to *AI Gateway* > *Providers* in the Redpanda Cloud console +. Navigate to *AI Gateway* > *Providers* in ADP . Select *Anthropic* from the provider list . Click *Add configuration* . Enter your Anthropic API key @@ -378,7 +378,7 @@ Continue.dev clients authenticate using bearer tokens. === Generate API tokens -. Navigate to *Security* > *API Tokens* in the Redpanda Cloud console +. Navigate to *Security* > *API Tokens* in ADP . Click *Create Token* . Enter token details: + diff --git a/modules/ROOT/partials/integrations/continue-user.adoc b/modules/ROOT/partials/integrations/continue-user.adoc index 0c8e925..476d9ff 100644 --- a/modules/ROOT/partials/integrations/continue-user.adoc +++ b/modules/ROOT/partials/integrations/continue-user.adoc @@ -302,7 +302,7 @@ After configuring Continue.dev, verify it connects correctly to your AI Gateway. Then verify in the AI Gateway dashboard: -. Open the Redpanda Cloud Console +. Sign in to ADP . Navigate to your gateway's observability dashboard . Filter by gateway ID . Verify: @@ -529,7 +529,7 @@ curl -H "Authorization: Bearer YOUR_API_KEY" \ /v1/models ---- + -You should receive a list of available models. If you get `401 Unauthorized`, regenerate your API key in the Redpanda Cloud Console. +You should receive a list of available models. If you get `401 Unauthorized`, regenerate your API key in ADP. . **Invalid JSON syntax** + diff --git a/modules/ROOT/partials/integrations/cursor-admin.adoc b/modules/ROOT/partials/integrations/cursor-admin.adoc index c5a64a7..ecbf4b4 100644 --- a/modules/ROOT/partials/integrations/cursor-admin.adoc +++ b/modules/ROOT/partials/integrations/cursor-admin.adoc @@ -58,7 +58,7 @@ Cursor IDE works with multiple providers through OpenAI-compatible transforms. E Cursor sends OpenAI-formatted requests but can route to Anthropic models. Configure the gateway to transform these requests: -. Navigate to *AI Gateway* > *Providers* in the Redpanda Cloud console +. Navigate to *AI Gateway* > *Providers* in ADP . Select *Anthropic* from the provider list . Click *Add configuration* . Enter your Anthropic API key @@ -342,7 +342,7 @@ Cursor clients authenticate using bearer tokens in the `Authorization` header. === Generate API tokens -. Navigate to *Security* > *API Tokens* in the Redpanda Cloud console +. Navigate to *Security* > *API Tokens* in ADP . Click *Create Token* . Enter token details: + diff --git a/modules/ROOT/partials/integrations/cursor-user.adoc b/modules/ROOT/partials/integrations/cursor-user.adoc index 7f4b69b..f78513a 100644 --- a/modules/ROOT/partials/integrations/cursor-user.adoc +++ b/modules/ROOT/partials/integrations/cursor-user.adoc @@ -319,7 +319,7 @@ After configuring Cursor IDE, verify it connects correctly to your AI Gateway. Then verify in the AI Gateway dashboard: -. Open the Redpanda Cloud Console +. Sign in to ADP . Navigate to your gateway's observability dashboard . Filter by gateway ID . Verify: @@ -513,7 +513,7 @@ curl -H "Authorization: Bearer YOUR_API_KEY" \ /models ---- + -You should receive a list of available models. If you get `401 Unauthorized`, regenerate your API key in the Redpanda Cloud Console. +You should receive a list of available models. If you get `401 Unauthorized`, regenerate your API key in ADP. . **Gateway endpoint URL mismatch** + @@ -665,7 +665,7 @@ Check if `.vscode/settings.json` in your project root overrides global settings . **Gateway geographic distance** + -If your gateway is in a different region than you or the upstream provider, this adds network latency. Check gateway region in the Redpanda Cloud Console. +If your gateway is in a different region than you or the upstream provider, this adds network latency. Check gateway region in ADP. . **Provider pool failover** + diff --git a/modules/ROOT/partials/integrations/github-copilot-admin.adoc b/modules/ROOT/partials/integrations/github-copilot-admin.adoc index 91ccb9e..a486cb3 100644 --- a/modules/ROOT/partials/integrations/github-copilot-admin.adoc +++ b/modules/ROOT/partials/integrations/github-copilot-admin.adoc @@ -59,7 +59,7 @@ GitHub Copilot works with multiple providers through OpenAI-compatible transform GitHub Copilot uses OpenAI by default. To enable OpenAI through the gateway: -. Navigate to *AI Gateway* > *Providers* in the Redpanda Cloud console +. Navigate to *AI Gateway* > *Providers* in ADP . Select *OpenAI* from the provider list . Click *Add configuration* . Enter your OpenAI API key @@ -290,7 +290,7 @@ GitHub Copilot clients authenticate using bearer tokens in the `Authorization` h === Generate API tokens -. Navigate to *Security* > *API Tokens* in the Redpanda Cloud console +. Navigate to *Security* > *API Tokens* in ADP . Click *Create Token* . Enter token details: + diff --git a/modules/ROOT/partials/integrations/github-copilot-user.adoc b/modules/ROOT/partials/integrations/github-copilot-user.adoc index 3d533f9..ec665db 100644 --- a/modules/ROOT/partials/integrations/github-copilot-user.adoc +++ b/modules/ROOT/partials/integrations/github-copilot-user.adoc @@ -449,7 +449,7 @@ Chat requests appear in the gateway dashboard with: === Verify in dashboard -. Open the Redpanda Cloud Console +. Sign in to ADP . Navigate to your gateway's observability dashboard . Filter by gateway ID . Verify: @@ -599,7 +599,7 @@ curl -H "Authorization: Bearer YOUR_API_KEY" \ https://gw.ai.panda.com/v1/models ---- + -You should receive a list of available models. If you get `401 Unauthorized`, regenerate your API key in the Redpanda Cloud Console. +You should receive a list of available models. If you get `401 Unauthorized`, regenerate your API key in ADP. . **Extension/plugin disabled** + @@ -654,7 +654,7 @@ echo $REDPANDA_API_KEY # Should print your API key . **Gateway geographic distance** + -If your gateway is in a different region than you or the upstream provider, this adds network latency. Check gateway region in the Redpanda Cloud Console. +If your gateway is in a different region than you or the upstream provider, this adds network latency. Check gateway region in ADP. . **Slow model for completion** + @@ -764,7 +764,7 @@ gpt-5.2 + Verify the model is enabled in your AI Gateway configuration: + -.. Open Redpanda Cloud Console +.. Sign in to ADP .. Navigate to your gateway .. Check enabled providers and models diff --git a/modules/ROOT/partials/migration-guide.adoc b/modules/ROOT/partials/migration-guide.adoc index dd39df1..fac2184 100644 --- a/modules/ROOT/partials/migration-guide.adoc +++ b/modules/ROOT/partials/migration-guide.adoc @@ -16,7 +16,7 @@ This guide helps you migrate existing applications from direct LLM provider inte Before migrating, ensure you have: -* AI Gateway configured in your Redpanda Cloud account +* AI Gateway configured in your ADP account * Enabled providers and models in AI Gateway * Created gateway with appropriate policies * Your gateway endpoint URL (with the gateway ID embedded in the path) diff --git a/modules/ROOT/partials/observability-logs.adoc b/modules/ROOT/partials/observability-logs.adoc index 6f909ba..c9c4a44 100644 --- a/modules/ROOT/partials/observability-logs.adoc +++ b/modules/ROOT/partials/observability-logs.adoc @@ -11,7 +11,7 @@ AI Gateway logs every LLM request that passes through it, capturing the full req == Before you begin * You have an active AI Gateway with at least one request processed. -* You have access to the Redpanda Cloud Console. +* You have access to ADP. * You have the appropriate permissions to view gateway logs. Use logs for: diff --git a/modules/ROOT/partials/observability-metrics.adoc b/modules/ROOT/partials/observability-metrics.adoc index 54d6b7a..15b8ca5 100644 --- a/modules/ROOT/partials/observability-metrics.adoc +++ b/modules/ROOT/partials/observability-metrics.adoc @@ -11,7 +11,7 @@ AI Gateway provides aggregate metrics and analytics dashboards to help you under == Before you begin * You have an active AI Gateway with at least one request processed. -* You have access to the Redpanda Cloud Console. +* You have access to ADP. * You have the appropriate permissions to view gateway metrics. Use metrics for: diff --git a/modules/ROOT/partials/service-account-authorization.adoc b/modules/ROOT/partials/service-account-authorization.adoc index ded9947..5cf307a 100644 --- a/modules/ROOT/partials/service-account-authorization.adoc +++ b/modules/ROOT/partials/service-account-authorization.adoc @@ -1,7 +1,7 @@ [[service-account-authorization]] == Service account authorization -When you create an MCP server or AI agent, Redpanda Cloud automatically creates a service account to authenticate requests to your cluster. The service account is created with the following: +When you create an MCP server or AI agent, ADP automatically creates a service account to authenticate requests to ADP resources. The service account is created with the following: *Name*: Prepopulated as `cluster----sa`, where `sa` stands for service account. For example: diff --git a/modules/agents/pages/a2a-concepts.adoc b/modules/agents/pages/a2a-concepts.adoc index 93b31af..f42321a 100644 --- a/modules/agents/pages/a2a-concepts.adoc +++ b/modules/agents/pages/a2a-concepts.adoc @@ -6,7 +6,7 @@ :learning-objective-2: Explain how agent cards enable discovery :learning-objective-3: Identify how authentication secures agent communication -The Agent-to-Agent (A2A) protocol is an open standard for agent communication and discovery. Redpanda Cloud uses A2A for both external integration and internal pipeline-to-agent communication. +The Agent-to-Agent (A2A) protocol is an open standard for agent communication and discovery. ADP uses A2A for both external integration and internal pipeline-to-agent communication. After reading this page, you will be able to: @@ -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 -Redpanda Cloud 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 Redpanda Cloud Console 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 ADP 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`. @@ -46,13 +46,13 @@ The `.well-known` path follows internet standards for service discovery, making To configure the agent card, see xref:create-agent.adoc#configure-a2a-discovery-metadata-optional[Configure A2A discovery metadata]. -== Where A2A is used in Redpanda Cloud +== Where A2A is used in ADP -Redpanda Cloud uses the A2A protocol in two contexts: +ADP uses the A2A protocol in two contexts: === External integration -External applications and agents hosted outside Redpanda Cloud use A2A to call Redpanda Cloud agents. This includes backend services, CLI tools, custom UIs, and agents hosted on other platforms. +External applications and agents hosted outside ADP use A2A to call ADP agents. This includes backend services, CLI tools, custom UIs, and agents hosted on other platforms. For integration pattern guidance, see xref:integration-overview.adoc[]. @@ -85,7 +85,7 @@ This discovery model allows: A2A-compliant agents require authentication to prevent unauthorized access. -Redpanda Cloud agents use OAuth2 client credentials flow. When you create an agent, the system provisions a service account with a client ID and secret. +ADP agents use OAuth2 client credentials flow. When you create an agent, the system provisions a service account with a client ID and secret. External callers use these credentials to obtain access tokens: @@ -108,7 +108,7 @@ For step-by-step authentication instructions, see xref:redpanda-cloud:security:c === Internal integration -The `a2a_message` processor handles authentication automatically. Pipelines don't need to manage credentials explicitly because they run within the Redpanda Cloud cluster with appropriate permissions. +The `a2a_message` processor handles authentication automatically. Pipelines don't need to manage credentials explicitly because they run within ADP with appropriate permissions. == Protocol versions diff --git a/modules/agents/pages/architecture-patterns.adoc b/modules/agents/pages/architecture-patterns.adoc index 02ce3da..02366e5 100644 --- a/modules/agents/pages/architecture-patterns.adoc +++ b/modules/agents/pages/architecture-patterns.adoc @@ -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 Redpanda Cloud Console, 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 ADP UI, then gradually move tools and responsibilities to the new subagents. == Root agent with subagents pattern @@ -87,7 +87,7 @@ A multi-agent architecture uses a root agent that delegates to specialized inter This pattern works for complex domains spanning multiple areas, multiple data sources with different access patterns, and tasks requiring specialized expertise within one deployment. -NOTE: Subagents in Redpanda Cloud are internal specialists within a single agent. They share the parent agent's model, budget, and policies, but each can have different names, descriptions, system prompts, and MCP tools. +NOTE: Subagents in ADP are internal specialists within a single agent. They share the parent agent's model, budget, and policies, but each can have different names, descriptions, system prompts, and MCP tools. === How it works @@ -109,11 +109,11 @@ Internal subagents provide domain isolation, allowing you to update the order su External A2A integration connects agents across organizational boundaries, platforms, or independent systems. -NOTE: Cross-agent calling between separate Redpanda Cloud agents is not supported. This pattern only applies to connecting Redpanda Cloud agents with external agents you host elsewhere. +NOTE: Cross-agent calling between separate ADP agents is not supported. This pattern only applies to connecting ADP agents with external agents you host elsewhere. === When to use external A2A -Use external glossterm:Agent2Agent (A2A) protocol[] for multi-organization workflows that coordinate agents across company boundaries, for platform integration connecting Redpanda Cloud agents with agents hosted elsewhere, and when agents require different deployment environments such as GPU clusters, air-gapped networks, or regional constraints. +Use external glossterm:Agent2Agent (A2A) protocol[] for multi-organization workflows that coordinate agents across company boundaries, for platform integration connecting ADP agents with agents hosted elsewhere, and when agents require different deployment environments such as GPU clusters, air-gapped networks, or regional constraints. === How it works @@ -123,7 +123,7 @@ Agents communicate using the xref:a2a-concepts.adoc[A2A protocol], a standard HT A customer service workflow might span multiple platforms: -* Redpanda Cloud agent accesses real-time order and inventory data +* ADP agent accesses real-time order and inventory data * CRM agent hosted elsewhere manages customer profiles and support tickets * Payment agent from a third party handles transactions in a secure environment @@ -157,7 +157,7 @@ Split into domain-specific subagents instead. Each subagent gets a focused promp === The tool explosion -A tool explosion occurs when a single agent has too many tools from every MCP server in the cluster. +A tool explosion occurs when a single agent has too many tools from every MCP server in the environment. This pattern fails because: @@ -199,7 +199,7 @@ For best results: == Model selection guide -Choose models based on task complexity, latency requirements, and cost constraints. The Redpanda Cloud Console displays available models with descriptions when creating agents. +Choose models based on task complexity, latency requirements, and cost constraints. The ADP UI displays available models with descriptions when creating agents. === Match models to task complexity diff --git a/modules/agents/pages/concepts.adoc b/modules/agents/pages/concepts.adoc index 2a743dd..0acd428 100644 --- a/modules/agents/pages/concepts.adoc +++ b/modules/agents/pages/concepts.adoc @@ -110,7 +110,7 @@ MCP tools extend agent capabilities beyond text generation. Understanding when a === Synchronous tool execution -In Redpanda Cloud, tool calls block the agent. When the agent decides to invoke a tool, it pauses and waits while the tool executes (querying a database, calling an API, or processing data). When the tool returns its result, the agent resumes reasoning. +In ADP, tool calls block the agent. When the agent decides to invoke a tool, it pauses and waits while the tool executes (querying a database, calling an API, or processing data). When the tool returns its result, the agent resumes reasoning. This synchronous model means latency adds up across multiple tool calls, the agent sees tool results sequentially rather than in parallel, and long-running tools can delay or fail agent requests due to timeouts. diff --git a/modules/agents/pages/create-agent.adoc b/modules/agents/pages/create-agent.adoc index c6ab304..674dbca 100644 --- a/modules/agents/pages/create-agent.adoc +++ b/modules/agents/pages/create-agent.adoc @@ -6,7 +6,7 @@ :learning-objective-2: Connect MCP servers and select tools for your agent :learning-objective-3: Set agent execution parameters including max iterations -Create a new AI agent declaratively through the Redpanda Cloud Console. No Python or JavaScript code required. This guide walks you through configuring the agent's model, writing the system prompt, connecting tools from built-in connectors, and setting execution parameters. +Create a new AI agent declaratively through the ADP UI. No Python or JavaScript code required. This guide walks you through configuring the agent's model, writing the system prompt, connecting tools from built-in connectors, and setting execution parameters. After reading this page, you will be able to: @@ -16,15 +16,14 @@ After reading this page, you will be able to: == Prerequisites -* A xref:redpanda-cloud:get-started:cluster-types/byoc/index.adoc[BYOC cluster]. +* An ADP BYOC environment. * xref:ai-gateway:gateway-quickstart.adoc[AI Gateway configured] with at least one LLM provider enabled. * At least one xref:mcp:overview.adoc[Remote MCP server] deployed with tools. * System prompt prepared (see xref:system-prompts.adoc[System Prompt Best Practices]). == Access the agents UI -. Log in to the link:https://cloud.redpanda.com[Redpanda Cloud Console^]. -. Navigate to your cluster. +. Sign in to ADP. . Click *Agentic AI* > *AI Agents* in the left navigation. == Configure basic settings @@ -126,7 +125,7 @@ For complete prompt guidelines, see xref:system-prompts.adoc[System Prompt Best == Add MCP servers and select tools . In the *Tools* section, click *Add MCP Server*. -. Select an MCP server from your cluster. +. Select an MCP server from those registered in ADP. . The UI displays all tools exposed by that server. . Select which tools this agent can use: + @@ -210,7 +209,7 @@ The updated metadata appears immediately at `\https://your-agent-url/.well-known . Configure the service account name (optional): + -A service account is automatically created to authenticate your agent with cluster resources. The default name follows the pattern `cluster--agent--sa`. You can customize this name (3-128 characters, cannot contain `<` or `>` characters). +A service account is automatically created to authenticate your agent with ADP resources. You can customize the default name (3-128 characters, cannot contain `<` or `>` characters). + For details about default permissions and how to manage service accounts, see xref:concepts.adoc#service-account-authorization[Service account authorization]. @@ -218,15 +217,11 @@ For details about default permissions and how to manage service accounts, see xr . Wait for agent creation to complete. -When your agent is running, Redpanda Cloud provides an HTTP endpoint URL with the pattern: - ----- -https://.ai-agents.. ----- +When your agent is running, ADP provides an HTTP endpoint URL. The exact form is shown on the agent's overview page; copy the value from the *Endpoint* field there. You can use this URL to call your agent programmatically or integrate it with external systems. -The *Inspector* tab in the Cloud Console automatically uses this URL to connect to your agent for testing. +The *Inspector* tab in ADP automatically uses this URL to connect to your agent for testing. For programmatic access or external agent integration, see xref:integration-overview.adoc[]. diff --git a/modules/agents/pages/get-started-index.adoc b/modules/agents/pages/get-started-index.adoc index 29964e6..aa08dab 100644 --- a/modules/agents/pages/get-started-index.adoc +++ b/modules/agents/pages/get-started-index.adoc @@ -1,5 +1,5 @@ = Get Started with AI Agents :page-layout: index -:description: Get started with declarative AI agents in Redpanda Cloud. Connect tools, configure behavior, and deploy without writing agent code. +:description: Get started with declarative AI agents in ADP. Connect tools, configure behavior, and deploy without writing agent code. Start here to create your first declarative AI agent. Select an LLM, define behavior, and connect tools from built-in connectors. diff --git a/modules/agents/pages/index.adoc b/modules/agents/pages/index.adoc index e2527fa..6bb731e 100644 --- a/modules/agents/pages/index.adoc +++ b/modules/agents/pages/index.adoc @@ -1,4 +1,4 @@ = AI Agents :page-layout: index -:description: Declare agent behavior using built-in connectors in Redpanda Cloud. No custom agent code required. +:description: Declare agent behavior using built-in connectors. No custom agent code required. diff --git a/modules/agents/pages/integration-overview.adoc b/modules/agents/pages/integration-overview.adoc index 92c2ccf..d522374 100644 --- a/modules/agents/pages/integration-overview.adoc +++ b/modules/agents/pages/integration-overview.adoc @@ -6,7 +6,7 @@ :learning-objective-2: Apply appropriate authentication for internal versus external integration :learning-objective-3: Select the right communication protocol for your integration scenario -Redpanda Cloud supports multiple integration patterns for agents, pipelines, and external applications. Choose the pattern that matches your integration scenario. +ADP supports multiple integration patterns for agents, pipelines, and external applications. Choose the pattern that matches your integration scenario. After reading this page, you will be able to: @@ -16,7 +16,7 @@ After reading this page, you will be able to: == Integration scenarios -Redpanda Cloud supports three primary integration scenarios based on who initiates the call and where the caller is located: +ADP supports three primary integration scenarios based on who initiates the call and where the caller is located: [cols="1,2,2,1"] |=== @@ -33,7 +33,7 @@ Redpanda Cloud supports three primary integration scenarios based on who initiat | xref:pipeline-integration-patterns.adoc[] | External system calls agent -| Your application or agent (hosted outside Redpanda Cloud) calls Redpanda Cloud agents using the A2A protocol +| Your application or agent (hosted outside ADP) calls ADP agents using the A2A protocol | Backend services, CLI tools, custom UIs, multi-platform agent workflows | xref:a2a-concepts.adoc[] |=== @@ -68,7 +68,7 @@ For implementation details, see xref:pipeline-integration-patterns.adoc[]. === External system calls agent -Use external integration when your applications, services, or agents hosted outside Redpanda Cloud need to call Redpanda Cloud agents. +Use external integration when your applications, services, or agents hosted outside ADP need to call ADP agents. External systems send requests using the A2A protocol and receive responses synchronously. This works for backend services, CLI tools, custom UIs, and agents hosted on other platforms. @@ -111,7 +111,7 @@ The following table compares the two primary internal integration patterns: == Security considerations for external integration -When integrating external applications with Redpanda Cloud agents, protect credentials and tokens. +When integrating external applications with ADP agents, protect credentials and tokens. === Protect service account credentials diff --git a/modules/agents/pages/monitor.adoc b/modules/agents/pages/monitor.adoc index c0a6c68..6e7c727 100644 --- a/modules/agents/pages/monitor.adoc +++ b/modules/agents/pages/monitor.adoc @@ -79,7 +79,7 @@ The *Inspector* tab provides real-time conversation testing. Use it to test agen === Access Inspector -. Navigate to *Agentic AI* > *AI Agents* in the Redpanda Cloud Console. +. In ADP, navigate to *Agentic AI* > *AI Agents*. . Click your agent name. . Open the *Inspector* tab. . Enter test queries and review responses. diff --git a/modules/agents/pages/overview.adoc b/modules/agents/pages/overview.adoc index 9f89282..3fb0861 100644 --- a/modules/agents/pages/overview.adoc +++ b/modules/agents/pages/overview.adoc @@ -1,13 +1,13 @@ = AI Agents Overview :page-aliases: redpanda-cloud:ai-agents:agents/overview.adoc -:description: Learn how Redpanda Cloud agents use a declarative approach backed by 300+ built-in connectors to replace custom agent code. +:description: Learn how ADP agents use a declarative approach backed by 300+ built-in connectors to replace custom agent code. :page-topic-type: overview :personas: evaluator, agent_developer, app_developer, streaming_developer :learning-objective-1: Describe what AI agents are and their essential components -:learning-objective-2: Explain how Redpanda Cloud streaming infrastructure benefits agent architectures -:learning-objective-3: Identify use cases where Redpanda Cloud agents provide value +:learning-objective-2: Explain how ADP streaming infrastructure benefits agent architectures +:learning-objective-3: Identify use cases where ADP agents provide value -AI agents in Redpanda Cloud take a declarative approach: instead of writing Python or JavaScript agent code, you declare the behavior you want by selecting an LLM, writing a system prompt, and connecting tools drawn from 300+ built-in Redpanda Connect connectors. The framework handles execution, tool orchestration, and scaling, backed by real-time streaming infrastructure and built-in filtering and data enrichment. +ADP AI agents take a declarative approach: instead of writing Python or JavaScript agent code, you declare the behavior you want by selecting an LLM, writing a system prompt, and connecting tools drawn from 300+ built-in Redpanda Connect connectors. The framework handles execution, tool orchestration, and scaling, backed by real-time streaming infrastructure and built-in filtering and data enrichment. After reading this page, you will be able to: @@ -17,11 +17,11 @@ After reading this page, you will be able to: == What is an AI agent? -An AI agent is a system built around a glossterm:large language model (LLM)[] that interprets user intent, selects the right tools, and chains multiple steps into a workflow. In Redpanda Cloud, agents are declarative: you configure what the agent should do (its role, constraints, and available tools) rather than writing imperative agent code. This is possible because Redpanda Connect provides the connectors and robust data processing capabilities that the framework orchestrates for you. +An AI agent is a system built around a glossterm:large language model (LLM)[] that interprets user intent, selects the right tools, and chains multiple steps into a workflow. In ADP, agents are declarative: you configure what the agent should do (its role, constraints, and available tools) rather than writing imperative agent code. This is possible because Redpanda Connect provides the connectors and robust data processing capabilities that the framework orchestrates for you. == How agents work -When you create an agent, you configure the components through the Redpanda Cloud Console rather than writing code: +When you create an agent, you configure the components through the ADP 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 @@ -40,7 +40,7 @@ A declarative approach means you configure agent behavior instead of coding it, == Use cases -AI agents in Redpanda Cloud unlock new capabilities across multiple fields. +ADP AI agents unlock new capabilities across multiple fields. === For AI agent developers @@ -56,9 +56,9 @@ Process every event with AI reasoning at scale. Invoke agents automatically from == Limitations -* Agents are available only on xref:redpanda-cloud:get-started:cluster-types/byoc/index.adoc[BYOC clusters] -* MCP servers must be hosted in Redpanda Cloud clusters -* Cross-agent calling between separate agents hosted in Redpanda Cloud is not currently supported (use internal subagents for delegation within a single agent) +* Agents are available only on ADP BYOC environments +* MCP servers must be hosted in ADP +* Cross-agent calling between separate agents is not currently supported (use internal subagents for delegation within a single agent) == Next steps diff --git a/modules/agents/pages/quickstart.adoc b/modules/agents/pages/quickstart.adoc index 1a2396d..dbaff5a 100644 --- a/modules/agents/pages/quickstart.adoc +++ b/modules/agents/pages/quickstart.adoc @@ -1,13 +1,13 @@ = AI Agent Quickstart :page-aliases: redpanda-cloud:ai-agents:agents/quickstart.adoc -:description: Create your first AI agent in Redpanda Cloud that generates and publishes event data through natural language commands. +:description: Create your first AI agent in ADP that generates and publishes event data through natural language commands. :page-topic-type: tutorial :personas: agent_developer, evaluator -:learning-objective-1: Create an AI agent in Redpanda Cloud that uses MCP tools +: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 :learning-objective-3: Test the agent by generating and publishing events through natural language -This quickstart helps you build your first AI agent in Redpanda Cloud. You'll create an agent that understands natural language requests and uses MCP tools to generate and publish event data to Redpanda topics. +This quickstart helps you build your first AI agent in ADP. You'll create an agent that understands natural language requests and uses MCP tools to generate and publish event data to Redpanda topics. After completing this quickstart, you will be able to: @@ -17,7 +17,7 @@ After completing this quickstart, you will be able to: == Prerequisites -* A xref:redpanda-cloud:get-started:cluster-types/byoc/index.adoc[BYOC cluster] (agents are not available on Dedicated or Serverless clusters) +* An ADP BYOC environment (agents are not available on ADP Cloud yet) * xref:ai-gateway:gateway-quickstart.adoc[AI Gateway configured] with at least one LLM provider enabled (OpenAI, Anthropic, or Google AI) @@ -38,9 +38,9 @@ The agent orchestrates the `generate_input` and `redpanda_output` tools you crea == Create the agent -. Log in to the link:https://cloud.redpanda.com/[Redpanda Cloud Console^]. +. Sign in to ADP. -. Navigate to your cluster and click *Agentic AI* > *AI Agents* in the left navigation. +. Click *Agentic AI* > *AI Agents* in the left navigation. . Click *Create Agent*. @@ -60,7 +60,7 @@ The agent orchestrates the `generate_input` and `redpanda_output` tools you crea + [,text] ---- -You are an Event Data Manager agent for Redpanda Cloud. +You are an Event Data Manager agent for Redpanda. Your responsibilities: - Generate realistic fake user event data @@ -98,7 +98,7 @@ Response format: . Review your configuration and click *Create Agent*. + -TIP: A service account is automatically created to authenticate your agent with cluster resources. For details about default permissions and how to manage service accounts, see xref:concepts.adoc#service-account-authorization[Service account authorization]. +TIP: A service account is automatically created to authenticate your agent with ADP resources. For details about default permissions and how to manage service accounts, see xref:concepts.adoc#service-account-authorization[Service account authorization]. . Wait for the agent status to change from *Starting* to *Running*. diff --git a/modules/agents/pages/tutorials/customer-support-agent.adoc b/modules/agents/pages/tutorials/customer-support-agent.adoc index c1ccc2a..3d4a043 100644 --- a/modules/agents/pages/tutorials/customer-support-agent.adoc +++ b/modules/agents/pages/tutorials/customer-support-agent.adoc @@ -61,7 +61,7 @@ This granularity enables the agent to chain tools (check order status, see it's Create a Remote MCP server with the three tools. -. Navigate to your cluster in the link:https://cloud.redpanda.com[Redpanda Cloud Console^]. +. Sign in to ADP. . Go to *Agentic AI* > *Remote MCP*. . Click *Create MCP Server*. . Configure the server: @@ -180,7 +180,7 @@ Wait for the agent status to show *Running*. == Observe orchestration in action -Open the *Inspector* tab in the Redpanda Cloud Console to interact with the agent. +Open the *Inspector* tab in ADP to interact with the agent. Testing reveals how the agent makes decisions. Watch the conversation panel in the built-in chat interface to see the agent's reasoning process unfold. diff --git a/modules/agents/pages/tutorials/transaction-dispute-resolution.adoc b/modules/agents/pages/tutorials/transaction-dispute-resolution.adoc index 6e1829a..630a947 100644 --- a/modules/agents/pages/tutorials/transaction-dispute-resolution.adoc +++ b/modules/agents/pages/tutorials/transaction-dispute-resolution.adoc @@ -45,7 +45,7 @@ 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. -. Navigate to your cluster in the link:https://cloud.redpanda.com[Redpanda Cloud Console^]. +. Sign in to ADP. . Go to *Agentic AI* > *Remote MCP*. . Click *Create MCP Server*. . Configure the server: @@ -425,7 +425,7 @@ https://abc123.ai-agents.def456.cloud.redpanda.com/.well-known/agent-card.json Create the topics the pipeline will use for input and output. -. Go to *Topics* in the Redpanda Cloud Console. +. In ADP, go to *Topics*. . Click *Create Topic*. . Create the input topic: + @@ -444,7 +444,7 @@ Create the topics the pipeline will use for input and output. The pipeline needs SASL credentials to read from and write to Redpanda topics. -. Go to *Security* > *Users* in the Redpanda Cloud Console. +. In ADP, go to *Security* > *Users*. . Click *Create User*. . Configure the user: + @@ -480,7 +480,7 @@ The pipeline needs SASL credentials to read from and write to Redpanda topics. The pipeline needs SASL credentials stored as secrets to authenticate with Redpanda topics. -. Go to *Connect* > *Secrets* in the Redpanda Cloud Console (if not already there). +. In ADP, go to *Connect* > *Secrets* (if not already there). . Click *Create Secret*. . Create two secrets with these values: + @@ -489,7 +489,7 @@ The pipeline needs SASL credentials stored as secrets to authenticate with Redpa === Create the pipeline -. Go to *Connect* in the Redpanda Cloud Console. +. In ADP, go to *Connect*. . Click *Create a pipeline*. . In the numbered steps, click *4 Add permissions*. . Select *Service Account*. @@ -515,7 +515,7 @@ This pipeline: === Test the pipeline -. Authenticate with your Redpanda Cloud cluster: +. Authenticate with ADP: + [,bash] ---- diff --git a/modules/ai-gateway/pages/admin/setup-guide.adoc b/modules/ai-gateway/pages/admin/setup-guide.adoc index 32b2ade..7cd5b6a 100644 --- a/modules/ai-gateway/pages/admin/setup-guide.adoc +++ b/modules/ai-gateway/pages/admin/setup-guide.adoc @@ -16,7 +16,7 @@ After completing this guide, you will be able to: == Prerequisites -* Access to the Redpanda Cloud Console with administrator privileges +* Access to ADP with administrator privileges * API keys for at least one LLM provider (OpenAI, Anthropic, Google AI) * (Optional) MCP server endpoints if you plan to use tool aggregation @@ -24,7 +24,7 @@ After completing this guide, you will be able to: Providers represent upstream services (Anthropic, OpenAI, Google AI) and associated credentials. Providers are disabled by default and must be enabled explicitly by an administrator. -. In the Redpanda Cloud Console, navigate to *Agentic* → *AI Gateway* → *Providers*. +. In ADP, navigate to *Agentic* → *AI Gateway* → *Providers*. . Select a provider (for example, Anthropic). . On the Configuration tab for the provider, click *Add configuration*. . Enter your API Key for the provider. @@ -370,7 +370,7 @@ Expected result: Successful completion response. Now that your gateway is configured, share access with users (builders): . Provide the *Gateway Endpoint* (for example, `https://example/gateways/gw_abc123/v1`) -. Share API credentials (Redpanda Cloud tokens with appropriate permissions) +. Share API credentials (ADP tokens with appropriate permissions) . (Optional) Document available models and any routing policies . (Optional) Share rate limits and budget information diff --git a/modules/ai-gateway/pages/aggregation.adoc b/modules/ai-gateway/pages/aggregation.adoc index 103de18..768ea61 100644 --- a/modules/ai-gateway/pages/aggregation.adoc +++ b/modules/ai-gateway/pages/aggregation.adoc @@ -757,7 +757,7 @@ Possible causes: Solution: -1. Verify MCP server is active in the Redpanda Cloud console +1. Verify MCP server is active in ADP 2. Verify tool is in enabled_tools list 3. If deferred loading: Agent must call `search_tools` first @@ -823,7 +823,7 @@ Gateway → MCP server: Agent → Gateway: -* Standard gateway authentication (Redpanda Cloud token) +* Standard gateway authentication (ADP token) * Gateway endpoint URL identifies the gateway (and its approved MCP servers) === Audit trail diff --git a/modules/ai-gateway/pages/builders/discover-gateways.adoc b/modules/ai-gateway/pages/builders/discover-gateways.adoc index 29c1464..a529b8b 100644 --- a/modules/ai-gateway/pages/builders/discover-gateways.adoc +++ b/modules/ai-gateway/pages/builders/discover-gateways.adoc @@ -16,16 +16,16 @@ After reading this page, you will be able to: == Before you begin -* You have a Redpanda Cloud account with access to at least one AI Gateway -* You have access to the Redpanda Cloud Console or API credentials +* You have an ADP account with access to at least one AI Gateway +* You have access to ADP or API credentials == List your accessible gateways [tabs] ==== -Using the Console:: +Using the UI:: + -. Navigate to *Agentic* > *AI Gateway* > *Gateways* in the Redpanda Cloud Console. +. In ADP, navigate to *Agentic* > *AI Gateway* > *Gateways*. . Review the list of gateways you can access. For each gateway, you'll see the gateway name, ID, endpoint URL, status, available models, and provider performance. + Click the Configuration, API, MCP Tools, and Changelog tabs for additional information. diff --git a/modules/ai-gateway/pages/configure-provider.adoc b/modules/ai-gateway/pages/configure-provider.adoc index 63ae878..75516e1 100644 --- a/modules/ai-gateway/pages/configure-provider.adoc +++ b/modules/ai-gateway/pages/configure-provider.adoc @@ -17,9 +17,7 @@ After completing this guide, you will be able to: == Prerequisites -* Access to a Redpanda Cloud cluster with ADP enabled. -+ -// TODO: this guide describes the cluster-embedded view available today on cloud.redpanda.com. The standalone-ADP UI launches as a separate product surface; sign-in URL, IAM model, and role-permission requirements will change. Update once standalone ADP ships. +* Access to ADP. * An API key (or AWS credentials for Bedrock) for the upstream provider you want to configure. * One or more secrets already created in your dataplane's secret store for the provider's credentials. Secret references must use `UPPER_SNAKE_CASE`. For example: `OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, `AWS_ACCESS_KEY_ID`. + @@ -27,8 +25,8 @@ After completing this guide, you will be able to: == Open the Create LLM provider page -. Sign in to https://cloud.redpanda.com[cloud.redpanda.com] and open the cluster you want to configure. -. In the sidebar, expand *ADP* and select *LLM Providers*. +. Sign in to ADP. +. Open *LLM Providers* in the sidebar. . Click *Create provider*. The *Create LLM provider* page opens. == Fill in the Provider card @@ -232,12 +230,12 @@ The provider detail page shows whether Auth passthrough is enabled in the *Conne == Out of scope -AI Gateway does not provide these capabilities. For current status, consult the Redpanda Cloud release notes. +AI Gateway does not provide these capabilities. For current status, consult the ADP release notes. * *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. The provider detail page shows a *Cost & usage* placeholder labeled "Coming soon"; 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 *ADP* → *MCP Servers*. +* *Managed MCP aggregation at the gateway.* Register MCP tool servers separately under *MCP Servers* in the ADP UI. == Next steps diff --git a/modules/ai-gateway/pages/connect-agent.adoc b/modules/ai-gateway/pages/connect-agent.adoc index 31a2d00..c6d127d 100644 --- a/modules/ai-gateway/pages/connect-agent.adoc +++ b/modules/ai-gateway/pages/connect-agent.adoc @@ -93,8 +93,6 @@ When `rpai` isn't available (CI runners, server-side processes, headless agents) |`client_credentials` |=== -// TODO: confirm the audience for ADP once the standalone UI launches. The values above match today's cluster-embedded view. - [tabs] ====== cURL:: @@ -356,7 +354,7 @@ 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 Cloud UI on each provider's detail page. A *Cost & usage* section is in development (the UI shows a "Coming soon" placeholder today). +* *Observe usage* through the ADP UI on each provider's detail page. A *Cost & usage* section is in development (the UI shows a "Coming soon" placeholder today). == Troubleshooting diff --git a/modules/ai-gateway/pages/overview.adoc b/modules/ai-gateway/pages/overview.adoc index b101aff..838f614 100644 --- a/modules/ai-gateway/pages/overview.adoc +++ b/modules/ai-gateway/pages/overview.adoc @@ -1,5 +1,5 @@ = AI Gateway Overview -:description: AI Gateway is Redpanda's managed proxy for LLM APIs. Create a provider for OpenAI, Anthropic, Google AI, AWS Bedrock, or an OpenAI-compatible endpoint, and point your applications at a Redpanda-hosted URL with managed secrets, authentication, and observability. +:description: AI Gateway is ADP's managed proxy for LLM APIs. Create a provider for OpenAI, Anthropic, Google AI, AWS Bedrock, or an OpenAI-compatible endpoint, and point your applications at a Redpanda-hosted URL with managed secrets, authentication, and observability. :page-topic-type: overview :personas: platform_admin, app_developer, evaluator // TODO: Add 'redpanda-cloud:ai-agents:ai-gateway/what-is-ai-gateway.adoc' to page-aliases after ai-agents is removed from cloud-docs @@ -8,7 +8,7 @@ :learning-objective-2: Explain how LLM providers, secrets, and OIDC authentication fit together in AI Gateway :learning-objective-3: Identify use cases where AI Gateway fits, and use cases where it does not -AI Gateway is Redpanda's managed proxy for LLM APIs. Instead of giving every application a provider API key and letting it call the upstream directly, you create an *LLM provider* in Redpanda Cloud and point your applications at a Redpanda-hosted proxy URL. Redpanda handles the upstream credentials, forwards the request, and records usage. Your code continues to use the provider's native SDK. +AI Gateway is ADP's managed proxy for LLM APIs. Instead of giving every application a provider API key and letting it call the upstream directly, you create an *LLM provider* in ADP and point your applications at a Redpanda-hosted proxy URL. Redpanda handles the upstream credentials, forwards the request, and records usage. Your code continues to use the provider's native SDK. After reading this page, you will be able to: @@ -46,17 +46,15 @@ Use the provider's own SDK: OpenAI, Anthropic, Google AI, AWS Bedrock, or any Op === Managed authentication -Applications authenticate to Redpanda with OIDC service accounts instead of long-lived provider API keys. Service accounts live in Redpanda Cloud IAM, follow the same role and audit model as every other resource, and mint short-lived tokens that are easy to revoke. The recommended local flow uses the `rpai` CLI for token refresh; CI and programmatic clients use the OIDC client-credentials grant directly. See xref:connect-agent.adoc[Connect your agent]. +Applications authenticate to ADP with OIDC service accounts instead of long-lived provider API keys. Service accounts use the same role and audit model as every other ADP resource, and mint short-lived tokens that are easy to revoke. The recommended local flow uses the `rpai` CLI for token refresh; CI and programmatic clients use the OIDC client-credentials grant directly. See xref:connect-agent.adoc[Connect your agent]. === Per-provider observability -The provider's detail page in the Cloud UI records request and token counts. A *Cost & usage* section is in development (the UI shows a "Coming soon" placeholder today). +The provider's detail page in the ADP UI records request and token counts. A *Cost & usage* section is in development (the UI shows a "Coming soon" placeholder today). == What's in the UI -// TODO: this guide describes the cluster-embedded view available today on cloud.redpanda.com. The standalone-ADP UI launches as a separate product surface; sign-in URL, IAM model, and sidebar layout will change. Update this section once standalone ADP ships. - -In Redpanda Cloud, open your cluster and expand the *ADP* section in the sidebar. You'll see four sub-items: +In the ADP UI you'll find four areas: * *LLM Providers*: Create, edit, enable, and delete providers. This is the home of AI Gateway configuration. * *MCP Servers*: Register glossterm:MCP[] tool servers for agents. Separate from the AI Gateway proxy URL. @@ -97,7 +95,7 @@ AI Gateway is a good fit when you want to: * Pull provider API keys out of application code and manage them centrally. * Keep LLM traffic inside your dataplane's VPC and your secrets out of application code. -* Authenticate applications to LLMs using the same OIDC identity you use for other Redpanda Cloud resources. +* Authenticate applications to LLMs using the same OIDC identity you use for other ADP resources. * Run a self-hosted OpenAI-compatible endpoint (vLLM, Ollama, LM Studio) alongside 1P providers behind a single management plane. * Separate operator and developer roles. Operators configure providers and credentials; developers point at proxy URLs. @@ -109,12 +107,12 @@ It is not the right fit when you: [[out-of-scope]] == Out of scope -AI Gateway does not provide these capabilities. For current status, consult the Redpanda Cloud release notes. +AI Gateway does not provide these capabilities. For current status, consult the ADP release notes. * *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. The provider detail page shows a *Cost & usage* placeholder labeled "Coming soon"; see xref:governance:budgets.adoc[Token budgets and limits] for the read-only spending visibility shipping at GA. * *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 *ADP* → *MCP Servers*. +* *Managed MCP aggregation at the gateway.* Register MCP tool servers separately under *MCP Servers* in the ADP UI. == Next steps diff --git a/modules/ai-gateway/pages/routing-cel.adoc b/modules/ai-gateway/pages/routing-cel.adoc index 098a7e2..2aad059 100644 --- a/modules/ai-gateway/pages/routing-cel.adoc +++ b/modules/ai-gateway/pages/routing-cel.adoc @@ -949,4 +949,4 @@ Each request evaluates CEL expression once. Total latency impact: == Next steps -* *Apply CEL routing*: See the gateway configuration options available in the Redpanda Cloud console. +* *Apply CEL routing*: See the gateway configuration options available in ADP. diff --git a/modules/ai-gateway/partials/ai-hub/configure-ai-hub.adoc b/modules/ai-gateway/partials/ai-hub/configure-ai-hub.adoc index 2eb77ce..40a77f2 100644 --- a/modules/ai-gateway/partials/ai-hub/configure-ai-hub.adoc +++ b/modules/ai-gateway/partials/ai-hub/configure-ai-hub.adoc @@ -18,17 +18,17 @@ After reading this page, you will be able to: == Prerequisites -* Access to the Redpanda Cloud Console with administrator privileges +* Access to ADP with administrator privileges * API keys for at least one LLM provider: ** OpenAI: API key from https://platform.openai.com/api-keys ** Anthropic: API key from https://console.anthropic.com/settings/keys -* A Redpanda Cloud workspace +* An ADP workspace == Create an AI Hub gateway Creating an AI Hub gateway is significantly simpler than creating a Custom mode gateway because all routing rules and backend pools are pre-configured. -. In the Redpanda Cloud Console, navigate to *Agentic* → *AI Gateway* → *Gateways*. +. In ADP, navigate to *Agentic* → *AI Gateway* → *Gateways*. . Click *Create Gateway*. . Select *AI Hub* as the gateway mode. . Configure basic settings: diff --git a/modules/ai-gateway/partials/ai-hub/use-ai-hub-gateway.adoc b/modules/ai-gateway/partials/ai-hub/use-ai-hub-gateway.adoc index 9aec958..ab1b3e7 100644 --- a/modules/ai-gateway/partials/ai-hub/use-ai-hub-gateway.adoc +++ b/modules/ai-gateway/partials/ai-hub/use-ai-hub-gateway.adoc @@ -19,7 +19,7 @@ After reading this page, you will be able to: == Before you begin * You have access to at least one AI Hub gateway (provided by your administrator) -* You have a Redpanda Cloud API key +* You have an ADP API key * You have Python 3.8+ or Node.js 18+ installed (for code examples) == Identify an AI Hub gateway diff --git a/modules/get-started/pages/signup.adoc b/modules/get-started/pages/signup.adoc index 5af962e..20f6a71 100644 --- a/modules/get-started/pages/signup.adoc +++ b/modules/get-started/pages/signup.adoc @@ -1,5 +1,5 @@ = Sign Up for ADP Cloud -:description: Create your Redpanda Cloud account and get started with Agentic Data Plane. +:description: Create your ADP Cloud account and get started with the Agentic Data Plane. :page-cloud-only: true // TODO: Add content diff --git a/modules/integrations/partials/integrations/claude-code-admin.adoc b/modules/integrations/partials/integrations/claude-code-admin.adoc index 566da41..799e767 100644 --- a/modules/integrations/partials/integrations/claude-code-admin.adoc +++ b/modules/integrations/partials/integrations/claude-code-admin.adoc @@ -44,7 +44,7 @@ Claude Code requires access to LLM providers through the gateway. Enable at leas Claude Code uses Anthropic models by default. To enable Anthropic: -. Navigate to *AI Gateway* > *Providers* in the Redpanda Cloud console +. Navigate to *AI Gateway* > *Providers* in ADP . Select *Anthropic* from the provider list . Click *Add configuration* . Enter your Anthropic API key @@ -268,7 +268,7 @@ Claude Code clients authenticate using bearer tokens. === Generate API tokens -. Navigate to *Security* > *API Tokens* in the Redpanda Cloud console +. Navigate to *Security* > *API Tokens* in ADP . Click *Create Token* . Enter token details: + diff --git a/modules/integrations/partials/integrations/claude-code-user.adoc b/modules/integrations/partials/integrations/claude-code-user.adoc index 450f589..804794c 100644 --- a/modules/integrations/partials/integrations/claude-code-user.adoc +++ b/modules/integrations/partials/integrations/claude-code-user.adoc @@ -202,7 +202,7 @@ If deferred tool loading is enabled in your gateway, you'll see a search tool an Check that requests route through the gateway by monitoring the AI Gateway dashboard: -. Open the Redpanda Cloud Console +. Sign in to ADP . Navigate to your gateway's observability dashboard . Send a test request from Claude Code: + @@ -292,7 +292,7 @@ curl -H "Authorization: Bearer YOUR_API_KEY" \ /mcp ---- + -You should receive a valid MCP protocol response. If you get `401 Unauthorized`, regenerate your API key in the Redpanda Cloud Console. +You should receive a valid MCP protocol response. If you get `401 Unauthorized`, regenerate your API key in ADP. . **Gateway endpoint URL mismatch** + @@ -335,7 +335,7 @@ Ensure requests use the `vendor/model_id` format (for example, `anthropic/claude . **Gateway geographic distance** + -If your gateway is in a different region than you or the upstream provider, this adds network latency. Check gateway region in the Redpanda Cloud Console. +If your gateway is in a different region than you or the upstream provider, this adds network latency. Check gateway region in ADP. . **Provider pool failover** + diff --git a/modules/integrations/partials/integrations/cline-admin.adoc b/modules/integrations/partials/integrations/cline-admin.adoc index 856dd29..469286f 100644 --- a/modules/integrations/partials/integrations/cline-admin.adoc +++ b/modules/integrations/partials/integrations/cline-admin.adoc @@ -55,7 +55,7 @@ Cline requires access to LLM providers through the gateway. Enable at least one Cline uses Anthropic models by default. To enable Anthropic: -. Navigate to *AI Gateway* > *Providers* in the Redpanda Cloud console +. Navigate to *AI Gateway* > *Providers* in ADP . Select *Anthropic* from the provider list . Click *Add configuration* . Enter your Anthropic API key @@ -286,7 +286,7 @@ Cline clients authenticate using bearer tokens. === Generate API tokens -. Navigate to *Security* > *API Tokens* in the Redpanda Cloud console +. Navigate to *Security* > *API Tokens* in ADP . Click *Create Token* . Enter token details: + diff --git a/modules/integrations/partials/integrations/cline-user.adoc b/modules/integrations/partials/integrations/cline-user.adoc index 05a67c1..a337b7b 100644 --- a/modules/integrations/partials/integrations/cline-user.adoc +++ b/modules/integrations/partials/integrations/cline-user.adoc @@ -246,7 +246,7 @@ Send a test message in the Cline chat panel: Then verify in the AI Gateway dashboard: -. Open the Redpanda Cloud Console +. Sign in to ADP . Navigate to your gateway's observability dashboard . Filter by gateway ID . Verify: @@ -466,7 +466,7 @@ curl -H "Authorization: Bearer YOUR_API_KEY" \ /v1/models ---- + -You should receive a list of available models. If you get `401 Unauthorized`, regenerate your API key in the Redpanda Cloud Console. +You should receive a list of available models. If you get `401 Unauthorized`, regenerate your API key in ADP. . **Gateway endpoint URL mismatch** + @@ -715,7 +715,7 @@ This loads only essential tools initially. Cline queries for additional tools on Use AI Gateway spend limits to prevent runaway costs: -. Navigate to your gateway in the Redpanda Cloud Console +. Navigate to your gateway in ADP . Set monthly spend limit (for example, $500/month) . Configure alerts before reaching limit diff --git a/modules/integrations/partials/integrations/continue-admin.adoc b/modules/integrations/partials/integrations/continue-admin.adoc index 429a4b7..441ff31 100644 --- a/modules/integrations/partials/integrations/continue-admin.adoc +++ b/modules/integrations/partials/integrations/continue-admin.adoc @@ -58,7 +58,7 @@ Continue.dev works with multiple providers. Enable the providers your users will To enable Anthropic with native format support: -. Navigate to *AI Gateway* > *Providers* in the Redpanda Cloud console +. Navigate to *AI Gateway* > *Providers* in ADP . Select *Anthropic* from the provider list . Click *Add configuration* . Enter your Anthropic API key @@ -378,7 +378,7 @@ Continue.dev clients authenticate using bearer tokens. === Generate API tokens -. Navigate to *Security* > *API Tokens* in the Redpanda Cloud console +. Navigate to *Security* > *API Tokens* in ADP . Click *Create Token* . Enter token details: + diff --git a/modules/integrations/partials/integrations/continue-user.adoc b/modules/integrations/partials/integrations/continue-user.adoc index 0c8e925..476d9ff 100644 --- a/modules/integrations/partials/integrations/continue-user.adoc +++ b/modules/integrations/partials/integrations/continue-user.adoc @@ -302,7 +302,7 @@ After configuring Continue.dev, verify it connects correctly to your AI Gateway. Then verify in the AI Gateway dashboard: -. Open the Redpanda Cloud Console +. Sign in to ADP . Navigate to your gateway's observability dashboard . Filter by gateway ID . Verify: @@ -529,7 +529,7 @@ curl -H "Authorization: Bearer YOUR_API_KEY" \ /v1/models ---- + -You should receive a list of available models. If you get `401 Unauthorized`, regenerate your API key in the Redpanda Cloud Console. +You should receive a list of available models. If you get `401 Unauthorized`, regenerate your API key in ADP. . **Invalid JSON syntax** + diff --git a/modules/integrations/partials/integrations/cursor-admin.adoc b/modules/integrations/partials/integrations/cursor-admin.adoc index c5a64a7..ecbf4b4 100644 --- a/modules/integrations/partials/integrations/cursor-admin.adoc +++ b/modules/integrations/partials/integrations/cursor-admin.adoc @@ -58,7 +58,7 @@ Cursor IDE works with multiple providers through OpenAI-compatible transforms. E Cursor sends OpenAI-formatted requests but can route to Anthropic models. Configure the gateway to transform these requests: -. Navigate to *AI Gateway* > *Providers* in the Redpanda Cloud console +. Navigate to *AI Gateway* > *Providers* in ADP . Select *Anthropic* from the provider list . Click *Add configuration* . Enter your Anthropic API key @@ -342,7 +342,7 @@ Cursor clients authenticate using bearer tokens in the `Authorization` header. === Generate API tokens -. Navigate to *Security* > *API Tokens* in the Redpanda Cloud console +. Navigate to *Security* > *API Tokens* in ADP . Click *Create Token* . Enter token details: + diff --git a/modules/integrations/partials/integrations/cursor-user.adoc b/modules/integrations/partials/integrations/cursor-user.adoc index 7f4b69b..f78513a 100644 --- a/modules/integrations/partials/integrations/cursor-user.adoc +++ b/modules/integrations/partials/integrations/cursor-user.adoc @@ -319,7 +319,7 @@ After configuring Cursor IDE, verify it connects correctly to your AI Gateway. Then verify in the AI Gateway dashboard: -. Open the Redpanda Cloud Console +. Sign in to ADP . Navigate to your gateway's observability dashboard . Filter by gateway ID . Verify: @@ -513,7 +513,7 @@ curl -H "Authorization: Bearer YOUR_API_KEY" \ /models ---- + -You should receive a list of available models. If you get `401 Unauthorized`, regenerate your API key in the Redpanda Cloud Console. +You should receive a list of available models. If you get `401 Unauthorized`, regenerate your API key in ADP. . **Gateway endpoint URL mismatch** + @@ -665,7 +665,7 @@ Check if `.vscode/settings.json` in your project root overrides global settings . **Gateway geographic distance** + -If your gateway is in a different region than you or the upstream provider, this adds network latency. Check gateway region in the Redpanda Cloud Console. +If your gateway is in a different region than you or the upstream provider, this adds network latency. Check gateway region in ADP. . **Provider pool failover** + diff --git a/modules/integrations/partials/integrations/github-copilot-admin.adoc b/modules/integrations/partials/integrations/github-copilot-admin.adoc index 91ccb9e..a486cb3 100644 --- a/modules/integrations/partials/integrations/github-copilot-admin.adoc +++ b/modules/integrations/partials/integrations/github-copilot-admin.adoc @@ -59,7 +59,7 @@ GitHub Copilot works with multiple providers through OpenAI-compatible transform GitHub Copilot uses OpenAI by default. To enable OpenAI through the gateway: -. Navigate to *AI Gateway* > *Providers* in the Redpanda Cloud console +. Navigate to *AI Gateway* > *Providers* in ADP . Select *OpenAI* from the provider list . Click *Add configuration* . Enter your OpenAI API key @@ -290,7 +290,7 @@ GitHub Copilot clients authenticate using bearer tokens in the `Authorization` h === Generate API tokens -. Navigate to *Security* > *API Tokens* in the Redpanda Cloud console +. Navigate to *Security* > *API Tokens* in ADP . Click *Create Token* . Enter token details: + diff --git a/modules/integrations/partials/integrations/github-copilot-user.adoc b/modules/integrations/partials/integrations/github-copilot-user.adoc index 3d533f9..ec665db 100644 --- a/modules/integrations/partials/integrations/github-copilot-user.adoc +++ b/modules/integrations/partials/integrations/github-copilot-user.adoc @@ -449,7 +449,7 @@ Chat requests appear in the gateway dashboard with: === Verify in dashboard -. Open the Redpanda Cloud Console +. Sign in to ADP . Navigate to your gateway's observability dashboard . Filter by gateway ID . Verify: @@ -599,7 +599,7 @@ curl -H "Authorization: Bearer YOUR_API_KEY" \ https://gw.ai.panda.com/v1/models ---- + -You should receive a list of available models. If you get `401 Unauthorized`, regenerate your API key in the Redpanda Cloud Console. +You should receive a list of available models. If you get `401 Unauthorized`, regenerate your API key in ADP. . **Extension/plugin disabled** + @@ -654,7 +654,7 @@ echo $REDPANDA_API_KEY # Should print your API key . **Gateway geographic distance** + -If your gateway is in a different region than you or the upstream provider, this adds network latency. Check gateway region in the Redpanda Cloud Console. +If your gateway is in a different region than you or the upstream provider, this adds network latency. Check gateway region in ADP. . **Slow model for completion** + @@ -764,7 +764,7 @@ gpt-5.2 + Verify the model is enabled in your AI Gateway configuration: + -.. Open Redpanda Cloud Console +.. Sign in to ADP .. Navigate to your gateway .. Check enabled providers and models diff --git a/modules/mcp/pages/managed/kafka.adoc b/modules/mcp/pages/managed/kafka.adoc index 9cd1698..3847000 100644 --- a/modules/mcp/pages/managed/kafka.adoc +++ b/modules/mcp/pages/managed/kafka.adoc @@ -73,7 +73,7 @@ The Kafka managed type's authentication is part of its config, not the generic M |Username and password over TLS. Common for managed Kafka services. |`SCRAM-SHA-256` / `SCRAM-SHA-512` -|Salted challenge-response. Default for Redpanda Cloud. +|Salted challenge-response. Default for Redpanda. |`OAUTHBEARER` |Token-based; useful when fronting Kafka with an OAuth proxy. diff --git a/modules/observability/pages/concepts.adoc b/modules/observability/pages/concepts.adoc index 711281f..9094f19 100644 --- a/modules/observability/pages/concepts.adoc +++ b/modules/observability/pages/concepts.adoc @@ -68,7 +68,7 @@ Agent transcripts contain these span types: | Identify which model was called, measure LLM response time, and debug LLM API errors. | `rpcn-mcp` -| MCP tool invocation representing calls to Remote MCP servers. Shows tool execution time, including network latency and tool processing. Child spans with `instrumentationScope.name` set to `redpanda-connect` represent internal Redpanda Connect processing. +| MCP tool invocation representing calls to Remote MCP servers. Shows tool execution time, including network latency and tool processing. | Measure tool execution time and identify slow MCP tool calls. |=== @@ -102,7 +102,7 @@ MCP server transcripts contain these span types: | Measure total MCP server response time and identify slow tool invocations. | `service` -| Internal service processing span that appears at multiple levels in the hierarchy. Represents Redpanda Connect service operations including routing, processing, and component execution. +| Internal service processing span that appears at multiple levels in the hierarchy. Represents internal MCP server operations including routing, processing, and component execution. | Track internal processing overhead and identify where time is spent in the service layer. | Tool name (for example, `get_order_status`, `get_customer_history`) @@ -114,7 +114,7 @@ MCP server transcripts contain these span types: | Measure total processor pipeline execution time. | Processor name (for example, `mapping`, `http`, `branch`) -| Individual processor execution span representing a single Redpanda Connect processor. The span name matches the processor type. +| Individual processor execution span representing a single internal processor in the MCP server pipeline. The span name matches the processor type. | Identify slow processors and debug processing logic. |=== @@ -136,7 +136,7 @@ This shows: 3. Processor pipeline: 43 microseconds 4. Mapping processor: 18 microseconds (data transformation) -The majority of time (4+ seconds) is spent in tool execution, while internal processing (mapping) takes only microseconds. This indicates the tool itself (likely making external API calls or database queries) is the bottleneck, not Redpanda Connect's internal processing. +The majority of time (4+ seconds) is spent in tool execution, while internal processing (mapping) takes only microseconds. This indicates the tool itself (likely making external API calls or database queries) is the bottleneck, not the MCP server's internal processing. == Transcript layers and scope @@ -165,10 +165,6 @@ A complete agent transcript includes these layers: | MCP Server | `rpcn-mcp` | MCP server tool execution. Shows tool name, input parameters, result size, and execution time. Appears as a separate `service.name` in resource attributes. - -| Redpanda Connect -| `redpanda-connect` -| Internal Redpanda Connect component execution within MCP tools. Shows pipeline and individual component spans. |=== === How layers connect @@ -182,7 +178,7 @@ ai-agent-http-server (HTTP Server layer) ├── execute_tool get_order_status (AI SDK layer) │ └── HTTP POST (HTTP Client layer) │ └── get_order_status (MCP Server layer, different service) - │ └── processors (Redpanda Connect layer) + │ └── processors (MCP Server layer) └── chat gpt-5-nano (AI SDK layer, LLM call 2) ---- @@ -232,9 +228,6 @@ MCP Server layer: - Tool-specific attributes like `order_id`, `customer_id` - `result_prefix`, `result_length`: Tool result metadata - -Redpanda Connect layer: - - Component-specific attributes from your tool configuration The `scope.name` field identifies which instrumentation layer created each span. @@ -263,7 +256,7 @@ Each span captures a unit of work. Here's what a typical MCP tool invocation loo * `traceId` links all spans in the same request across services * `spanId` uniquely identifies this span * `name` identifies the operation or tool -* `instrumentationScope.name` identifies which layer created the span (`rpcn-mcp` for MCP tools, `redpanda-connect` for internal processing) +* `instrumentationScope.name` identifies which layer created the span (for example, `rpcn-mcp` for MCP tools) * `attributes` contain operation-specific metadata * `status.code` indicates success (0) or error (2) diff --git a/modules/observability/pages/ingest-custom-traces.adoc b/modules/observability/pages/ingest-custom-traces.adoc index 69fabd4..dc50f05 100644 --- a/modules/observability/pages/ingest-custom-traces.adoc +++ b/modules/observability/pages/ingest-custom-traces.adoc @@ -17,7 +17,7 @@ After reading this page, you will be able to: == Prerequisites -* A Redpanda Connect pipeline host (today: a BYOC Redpanda Cloud cluster with Connect enabled). Ability to manage secrets on that host. +* A Redpanda Connect pipeline host (today: a Redpanda BYOC cluster with Connect enabled). Ability to manage secrets on that host. // TODO: Replace with the standalone-ADP ingestion target once defined (may no longer require a Redpanda Cloud cluster). * The latest version of xref:manage:rpk/rpk-install.adoc[`rpk`] installed * Custom agent or application instrumented with OpenTelemetry SDK @@ -29,7 +29,7 @@ If you're using LangChain with OpenTelemetry tracing, you can send traces to Red . Configure LangChain's OpenTelemetry integration by following the https://docs.langchain.com/langsmith/trace-with-opentelemetry[LangChain documentation^]. -. Deploy a Redpanda Connect pipeline using the `otlp_http` input to receive OTLP traces over HTTP. Today, create the pipeline in the **Connect** page of your Redpanda Cloud cluster. See the <> section below for a sample configuration. +. Deploy a Redpanda Connect pipeline using the `otlp_http` input to receive OTLP traces over HTTP. Today, create the pipeline in the **Connect** page of your Redpanda BYOC cluster. See the <> section below for a sample configuration. // TODO: Update the deployment entry point once the standalone-ADP ingestion flow is defined. . Configure your OTEL exporter to send traces to your Redpanda Connect pipeline using environment variables: @@ -117,7 +117,7 @@ The `otlp_http` input component: * Accepts traces at the standard `/v1/traces` endpoint * Converts incoming OTLP data into individual Redpanda OTEL v1 Protobuf messages -The following example shows a minimal pipeline configuration. Redpanda Cloud automatically injects authentication handling, so you don't need to configure `auth_token` in the input. +The following example shows a minimal pipeline configuration. ADP automatically injects authentication handling, so you don't need to configure `auth_token` in the input. [,yaml] ---- @@ -145,7 +145,7 @@ The `otlp_grpc` input component: * Accepts traces via the OTLP gRPC protocol * Converts incoming OTLP data into individual Redpanda OTEL v1 Protobuf messages -The following example shows a minimal pipeline configuration. Redpanda Cloud automatically injects authentication handling. +The following example shows a minimal pipeline configuration. ADP automatically injects authentication handling. [,yaml] ---- @@ -173,7 +173,7 @@ The OTLP input automatically handles format conversion, so no processors are nee // TODO (standalone-ADP): Steps below assume a Redpanda Cloud cluster with Connect enabled. The standalone ADP product surface may expose a different deployment entry point. Revisit the whole subsection under Workflow #11. -. In the *Connect* page of your Redpanda Cloud cluster, click *Create Pipeline*. +. In the *Connect* page of your Redpanda BYOC cluster, click *Create Pipeline*. . For the input, select the *otlp_http* (or *otlp_grpc*) component. . Skip to *Add a topic* and select `redpanda.otel_traces` from the list of existing topics. Leave the default advanced settings. . In the *Add permissions* step, create a service account with write access to the `redpanda.otel_traces` topic. @@ -197,7 +197,7 @@ Configure your custom agent to send OpenTelemetry traces to the pipeline endpoin === Authenticate to the pipeline -The OTLP pipeline uses the same authentication mechanism as the Redpanda Cloud API (today, while ingestion runs on a Redpanda Cloud cluster). Obtain an access token using your service account credentials as described in xref:redpanda-cloud:security:cloud-authentication.adoc#authenticate-to-the-cloud-api[Authenticate to the Cloud API]. +The OTLP pipeline authenticates with a service account access token (today, while ingestion runs on a Redpanda BYOC cluster). Obtain an access token using your service account credentials as described in xref:redpanda-cloud:security:cloud-authentication.adoc#authenticate-to-the-cloud-api[Authenticate to the Cloud API]. // TODO (standalone-ADP): Update the auth model when the standalone ADP ingestion path is defined. Include the token in your requests: @@ -563,7 +563,7 @@ Check that traces are being published to the `redpanda.otel_traces` topic: rpk topic consume redpanda.otel_traces --offset end -n 10 ---- -You can also view the `redpanda.otel_traces` topic in the *Topics* page of the host UI (today, the Redpanda Cloud UI). +You can also view the `redpanda.otel_traces` topic in the *Topics* page of the host UI. Look for spans with your custom `instrumentationScope.name` to identify traces from your agent. diff --git a/modules/observability/partials/observability-logs.adoc b/modules/observability/partials/observability-logs.adoc index 6f909ba..c9c4a44 100644 --- a/modules/observability/partials/observability-logs.adoc +++ b/modules/observability/partials/observability-logs.adoc @@ -11,7 +11,7 @@ AI Gateway logs every LLM request that passes through it, capturing the full req == Before you begin * You have an active AI Gateway with at least one request processed. -* You have access to the Redpanda Cloud Console. +* You have access to ADP. * You have the appropriate permissions to view gateway logs. Use logs for: diff --git a/modules/observability/partials/observability-metrics.adoc b/modules/observability/partials/observability-metrics.adoc index 54d6b7a..15b8ca5 100644 --- a/modules/observability/partials/observability-metrics.adoc +++ b/modules/observability/partials/observability-metrics.adoc @@ -11,7 +11,7 @@ AI Gateway provides aggregate metrics and analytics dashboards to help you under == Before you begin * You have an active AI Gateway with at least one request processed. -* You have access to the Redpanda Cloud Console. +* You have access to ADP. * You have the appropriate permissions to view gateway metrics. Use metrics for: