From 9881f4b534acea7210e41b6206a5b8917b9fd3f5 Mon Sep 17 00:00:00 2001 From: micheleRP Date: Tue, 27 Jan 2026 11:53:54 -0700 Subject: [PATCH 01/11] update cloud overview adp focus --- modules/get-started/pages/cloud-overview.adoc | 57 ++++++++++++++++++- 1 file changed, 54 insertions(+), 3 deletions(-) diff --git a/modules/get-started/pages/cloud-overview.adoc b/modules/get-started/pages/cloud-overview.adoc index 57b85e371..b83146844 100644 --- a/modules/get-started/pages/cloud-overview.adoc +++ b/modules/get-started/pages/cloud-overview.adoc @@ -1,14 +1,57 @@ = Redpanda Cloud Overview -:description: Learn about Redpanda Serverless, Bring Your Own Cloud (BYOC), and Dedicated clusters. +:description: Learn about the Redpanda Agent Development Platform (ADP) and deployment options including BYOC, Dedicated, and Serverless clusters. :page-aliases: cloud:dedicated-byoc.adoc, deploy:deployment-option/cloud/dedicated-byoc.adoc, deploy:deployment-option/cloud/cloud-overview.adoc Redpanda Cloud is a complete data streaming platform delivered as a fully-managed service. It provides automated upgrades and patching, data balancing, and support while continuously monitoring your clusters and underlying infrastructure to meet strict performance, availability, reliability, and security requirements. All Redpanda Cloud clusters are deployed with an integrated glossterm:Redpanda Console[], and all clusters have access to unlimited retention and 300+ data connectors with xref:develop:connect/about.adoc[Redpanda Connect]. TIP: For more detailed information about the Redpanda platform, see xref:get-started:intro-to-events.adoc[] and xref:get-started:architecture.adoc[]. +== Redpanda Agent Development Platform (ADP) + +Redpanda Cloud delivers the Agent Development Platform (ADP), an enterprise-grade infrastructure for building, deploying, and managing AI agents at scale. ADP provides unified governance, observability, and security for agentic applications while leveraging Redpanda's streaming and analytical capabilities as the foundational data fabric. + +=== What is ADP? + +ADP combines multiple components into a cohesive platform: + +* **AI Agents**: Deploy declarative agents or bring your own agent frameworks (LangChain, LlamaIndex, and others) +* **MCP Servers**: Expose data and actions to agents through the Model Context Protocol, built on xref:develop:connect/about.adoc[Redpanda Connect] +* **AI Gateway**: Manage LLM provider access with cost controls, rate limiting, and intelligent routing +* **Catalog**: Centralized view of all agents, tools, and access policies across your organization + +=== Enterprise capabilities + +ADP addresses critical enterprise requirements for AI agent deployments: + +**Unified authorization**:: All components use OIDC-based authentication with an "on-behalf-of" authorization model. When a user invokes an agent, the agent inherits the intersection of its own permissions and the user's permissions, ensuring proper data access scoping. + +**Complete observability**:: ADP captures execution logs (agent transcripts) using OpenTelemetry standards with 100% trace sampling. View agent actions in Redpanda Console, query execution history with OXLA, and replay data for agent evaluations. + +**Compliance and audit**:: For industries requiring multi-year audit trails, ADP records every agent action and data source used in decision-making. Execution logs are stored in Redpanda topics and can be materialized to Iceberg tables for long-term retention and analysis. + +=== ADP deployment model + +ADP is primarily deployed using the <> model, where: + +* The **control plane** (managed by Redpanda) handles provisioning, monitoring, and policy management +* The **data plane** (deployed in your cloud account) runs the ADP components, Redpanda cluster, and OXLA query engine +* All your data remains in your infrastructure, providing maximum security and data sovereignty + +ADP installations include both Redpanda (for streaming and event storage) and OXLA (for SQL-based queries and analytics), forming the data fabric that powers agent applications. + +=== Use cases + +Organizations use ADP to: + +* **Extend Microsoft Copilot**: Integrate Office 365 agents with internal data sources that Copilot cannot access +* **Build domain-specific agents**: Create specialized agents for operational tasks, like querying building management systems or financial compliance workflows +* **Enable non-technical users**: Allow business users to interact with complex data through natural language interfaces instead of dashboards or SQL + +For details about building agents and MCP servers, see xref:ai-agents:index.adoc[]. + == Redpanda Cloud cluster types -Redpanda Cloud offers three fully-managed cloud deployment options, each designed for different use cases: +ADP and Redpanda Cloud applications are supported by three fully-managed deployment options. For ADP deployments, <> is the primary model, providing the security and data sovereignty required for enterprise agent platforms. For streaming applications, all three options are available: * **<>**: Fastest way to get started with automatic scaling * **<>**: Production clusters in Redpanda's cloud with enhanced isolation @@ -28,6 +71,11 @@ Redpanda Cloud offers three fully-managed cloud deployment options, each designe | Production clusters requiring cloud hosting, higher throughput, and extra isolation | Production clusters requiring data sovereignty, the highest throughput, and added security +| *ADP support* +| Development and testing +| Development and testing +| Production (primary deployment model) + | *Deployment* | Redpanda's cloud (AWS/GCP) | Redpanda's cloud (AWS/Azure/GCP) @@ -152,6 +200,8 @@ Redpanda creates a cloud organization for you and sends you a welcome email. === Bring Your Own Cloud (BYOC) +BYOC is the primary deployment model for the Agent Development Platform (ADP). With BYOC clusters, the Redpanda data plane (including ADP components, Redpanda brokers, and OXLA) deploys into your existing VPC or VNet, ensuring all data remains in your environment. + With BYOC clusters, you deploy the Redpanda glossterm:data plane[] into your existing VPC (for AWS and GCP) or VNet (for Azure), and all data is contained in your own environment. This provides an additional layer of security and isolation. (See xref:get-started:byoc-arch.adoc[].) Redpanda manages provisioning, monitoring, upgrades, and security policies, and it manages required resources in your VPC or VNet, including subnets (subnetworks in GCP), IAM roles, and object storage resources (for example, S3 buckets or Azure Storage accounts). @@ -392,10 +442,11 @@ The following features are currently in beta in Redpanda Cloud: * BYOVPC for AWS * BYOVNet for Azure * Secrets Management for BYOVPC on GCP and AWS -* xref:ai-agents:index.adoc[AI agents with MCP servers] +* xref:ai-agents:index.adoc[Agent Development Platform (ADP)] including AI agents, MCP servers, AI Gateway, and Catalog * Several Redpanda Connect components == Next steps +* xref:ai-agents:index.adoc[Build AI agents with ADP] * xref:manage:maintenance.adoc[Learn about upgrades and maintenance] * xref:get-started:cluster-types/serverless.adoc[Create a Serverless cluster] * xref:get-started:cluster-types/byoc/index.adoc[Create a BYOC cluster] From 090c1ef906cb1a0e07238f35d81cd2ba179f61be Mon Sep 17 00:00:00 2001 From: micheleRP Date: Tue, 27 Jan 2026 13:12:32 -0700 Subject: [PATCH 02/11] Update cloud overview with latest ADP content from CTO Tech Talk demo Align messaging with public demo content: emphasize manufacturing use case, add multi-agent architecture, highlight MCP server security features (injection attack prevention), strengthen interoperability messaging, and remove OXLA references not yet in public materials. Co-Authored-By: Claude Sonnet 4.5 --- modules/get-started/pages/cloud-overview.adoc | 24 ++++++++++--------- 1 file changed, 13 insertions(+), 11 deletions(-) diff --git a/modules/get-started/pages/cloud-overview.adoc b/modules/get-started/pages/cloud-overview.adoc index b83146844..022add19b 100644 --- a/modules/get-started/pages/cloud-overview.adoc +++ b/modules/get-started/pages/cloud-overview.adoc @@ -12,20 +12,22 @@ Redpanda Cloud delivers the Agent Development Platform (ADP), an enterprise-grad === What is ADP? -ADP combines multiple components into a cohesive platform: +ADP combines multiple components into a cohesive platform built on open standards for maximum interoperability: -* **AI Agents**: Deploy declarative agents or bring your own agent frameworks (LangChain, LlamaIndex, and others) -* **MCP Servers**: Expose data and actions to agents through the Model Context Protocol, built on xref:develop:connect/about.adoc[Redpanda Connect] -* **AI Gateway**: Manage LLM provider access with cost controls, rate limiting, and intelligent routing +* **AI Agents**: Deploy declarative agents or bring your own agent frameworks (LangChain, LlamaIndex, and others). Build multi-agent systems where specialized sub-agents handle specific responsibilities, following single-responsibility principles. +* **MCP Servers**: Build lightweight data and action interfaces using a low-code framework based on xref:develop:connect/about.adoc[Redpanda Connect]. Connect to hundreds of data sources (databases, cloud storage, APIs) and enforce fine-grained policies that programmatically prevent prompt injection and SQL injection attacks. MCP servers are extremely lightweight—run dozens on minimal resources—with OIDC-based access control and real-time debugging capabilities. +* **AI Gateway**: Manage LLM provider access with cost controls, rate limiting, intelligent routing, and failover support across multiple providers * **Catalog**: Centralized view of all agents, tools, and access policies across your organization === Enterprise capabilities ADP addresses critical enterprise requirements for AI agent deployments: +**Security by design**:: MCP servers enforce policies at the tool level, programmatically preventing prompt injection, SQL injection, and other agent-based attacks. Policy enforcement is deterministic and controlled—agents cannot bypass security constraints even through creative prompting. + **Unified authorization**:: All components use OIDC-based authentication with an "on-behalf-of" authorization model. When a user invokes an agent, the agent inherits the intersection of its own permissions and the user's permissions, ensuring proper data access scoping. -**Complete observability**:: ADP captures execution logs (agent transcripts) using OpenTelemetry standards with 100% trace sampling. View agent actions in Redpanda Console, query execution history with OXLA, and replay data for agent evaluations. +**Complete observability**:: ADP provides two levels of inspection: execution logs (transcripts) capture every agent action with 100% sampling using OpenTelemetry standards, while real-time debugging tools allow inspection of individual MCP server calls. Traces span across services and go as deep as needed—down to individual tool invocations with full timing data. View detailed agent actions in Redpanda Console and replay data for agent evaluations. **Compliance and audit**:: For industries requiring multi-year audit trails, ADP records every agent action and data source used in decision-making. Execution logs are stored in Redpanda topics and can be materialized to Iceberg tables for long-term retention and analysis. @@ -34,18 +36,18 @@ ADP addresses critical enterprise requirements for AI agent deployments: ADP is primarily deployed using the <> model, where: * The **control plane** (managed by Redpanda) handles provisioning, monitoring, and policy management -* The **data plane** (deployed in your cloud account) runs the ADP components, Redpanda cluster, and OXLA query engine +* The **data plane** (deployed in your cloud account) runs the ADP components and Redpanda cluster * All your data remains in your infrastructure, providing maximum security and data sovereignty -ADP installations include both Redpanda (for streaming and event storage) and OXLA (for SQL-based queries and analytics), forming the data fabric that powers agent applications. +ADP is built on open standards and protocols, allowing you to pick and choose components that fit your needs. Integrate with existing agent frameworks, data processing systems, or custom code—all components use standardized protocols for seamless interoperability. === Use cases Organizations use ADP to: -* **Extend Microsoft Copilot**: Integrate Office 365 agents with internal data sources that Copilot cannot access -* **Build domain-specific agents**: Create specialized agents for operational tasks, like querying building management systems or financial compliance workflows -* **Enable non-technical users**: Allow business users to interact with complex data through natural language interfaces instead of dashboards or SQL +* **Monitor manufacturing and operations**: Deploy multi-agent systems that analyze factory machine telemetry in real-time, detect anomalies, search equipment manuals, and create maintenance tickets automatically. Use data aggregation patterns (like tumbling windows) to process high-volume sensor data before sending insights to agents. +* **Extend enterprise productivity tools**: Integrate Microsoft Copilot or other workplace agents with internal data sources and systems that are otherwise inaccessible +* **Automate operational workflows**: Create specialized agents for building management, infrastructure monitoring, compliance reporting, and other domain-specific tasks For details about building agents and MCP servers, see xref:ai-agents:index.adoc[]. @@ -200,7 +202,7 @@ Redpanda creates a cloud organization for you and sends you a welcome email. === Bring Your Own Cloud (BYOC) -BYOC is the primary deployment model for the Agent Development Platform (ADP). With BYOC clusters, the Redpanda data plane (including ADP components, Redpanda brokers, and OXLA) deploys into your existing VPC or VNet, ensuring all data remains in your environment. +BYOC is the primary deployment model for the Agent Development Platform (ADP). With BYOC clusters, the Redpanda data plane (including ADP components and Redpanda brokers) deploys into your existing VPC or VNet, ensuring all data remains in your environment. With BYOC clusters, you deploy the Redpanda glossterm:data plane[] into your existing VPC (for AWS and GCP) or VNet (for Azure), and all data is contained in your own environment. This provides an additional layer of security and isolation. (See xref:get-started:byoc-arch.adoc[].) Redpanda manages provisioning, monitoring, upgrades, and security policies, and it manages required resources in your VPC or VNet, including subnets (subnetworks in GCP), IAM roles, and object storage resources (for example, S3 buckets or Azure Storage accounts). From e27797461269f86deaa47f3da0a721ad8458d80c Mon Sep 17 00:00:00 2001 From: micheleRP Date: Tue, 27 Jan 2026 15:25:44 -0700 Subject: [PATCH 03/11] cleanup --- modules/get-started/pages/cloud-overview.adoc | 77 ++++++++++--------- 1 file changed, 40 insertions(+), 37 deletions(-) diff --git a/modules/get-started/pages/cloud-overview.adoc b/modules/get-started/pages/cloud-overview.adoc index 022add19b..e54173c3f 100644 --- a/modules/get-started/pages/cloud-overview.adoc +++ b/modules/get-started/pages/cloud-overview.adoc @@ -1,59 +1,57 @@ = Redpanda Cloud Overview -:description: Learn about the Redpanda Agent Development Platform (ADP) and deployment options including BYOC, Dedicated, and Serverless clusters. +:description: Learn about the Redpanda Agentic Data Plane (ADP) and deployment options including BYOC, Dedicated, and Serverless clusters. :page-aliases: cloud:dedicated-byoc.adoc, deploy:deployment-option/cloud/dedicated-byoc.adoc, deploy:deployment-option/cloud/cloud-overview.adoc -Redpanda Cloud is a complete data streaming platform delivered as a fully-managed service. It provides automated upgrades and patching, data balancing, and support while continuously monitoring your clusters and underlying infrastructure to meet strict performance, availability, reliability, and security requirements. All Redpanda Cloud clusters are deployed with an integrated glossterm:Redpanda Console[], and all clusters have access to unlimited retention and 300+ data connectors with xref:develop:connect/about.adoc[Redpanda Connect]. +Redpanda Cloud is a complete data streaming and agentic data plane platform delivered as a fully-managed service. It provides automated upgrades and patching, data balancing, and support while continuously monitoring your clusters and underlying infrastructure to meet strict performance, availability, reliability, and security requirements. All Redpanda Cloud clusters are deployed with an integrated glossterm:Redpanda Console[], and all clusters have access to unlimited retention and 300+ data connectors with xref:develop:connect/about.adoc[Redpanda Connect]. -TIP: For more detailed information about the Redpanda platform, see xref:get-started:intro-to-events.adoc[] and xref:get-started:architecture.adoc[]. +== Redpanda Agentic Data Plane (ADP) -== Redpanda Agent Development Platform (ADP) +Redpanda ADP is an enterprise-grade infrastructure for building, deploying, and managing AI agents at scale. Redpanda ADP provides unified governance, observability, and security for agentic applications while leveraging Redpanda's streaming and analytical capabilities as the foundational data fabric. -Redpanda Cloud delivers the Agent Development Platform (ADP), an enterprise-grade infrastructure for building, deploying, and managing AI agents at scale. ADP provides unified governance, observability, and security for agentic applications while leveraging Redpanda's streaming and analytical capabilities as the foundational data fabric. +=== What is Redpanda ADP? -=== What is ADP? +Redpanda ADP combines multiple components into a cohesive platform built on open standards for maximum interoperability: -ADP combines multiple components into a cohesive platform built on open standards for maximum interoperability: - -* **AI Agents**: Deploy declarative agents or bring your own agent frameworks (LangChain, LlamaIndex, and others). Build multi-agent systems where specialized sub-agents handle specific responsibilities, following single-responsibility principles. -* **MCP Servers**: Build lightweight data and action interfaces using a low-code framework based on xref:develop:connect/about.adoc[Redpanda Connect]. Connect to hundreds of data sources (databases, cloud storage, APIs) and enforce fine-grained policies that programmatically prevent prompt injection and SQL injection attacks. MCP servers are extremely lightweight—run dozens on minimal resources—with OIDC-based access control and real-time debugging capabilities. -* **AI Gateway**: Manage LLM provider access with cost controls, rate limiting, intelligent routing, and failover support across multiple providers -* **Catalog**: Centralized view of all agents, tools, and access policies across your organization +* **AI agents**: Deploy declarative agents or bring your own agent frameworks (LangChain, LlamaIndex, and others). Build multi-agent systems where specialized sub-agents handle specific responsibilities, following single-responsibility principles. +* **MCP servers**: Build lightweight data and action interfaces using a low-code framework based on xref:develop:connect/about.adoc[Redpanda Connect]. Connect to hundreds of data sources (databases, cloud storage, APIs) and enforce fine-grained policies that programmatically prevent prompt injection and SQL injection attacks. MCP servers are extremely lightweight—run dozens on minimal resources—with OIDC-based access control and real-time debugging capabilities. +* **AI Gateway**: Manage LLM provider access with cost controls, rate limiting, intelligent routing, and failover support across multiple providers. +//* **Catalog**: Maintain a centralized repository of agents, MCP servers, tools, and policies. Share components across teams and enforce organization-wide standards. === Enterprise capabilities -ADP addresses critical enterprise requirements for AI agent deployments: +Redpanda ADP addresses critical enterprise requirements for AI agent deployments: -**Security by design**:: MCP servers enforce policies at the tool level, programmatically preventing prompt injection, SQL injection, and other agent-based attacks. Policy enforcement is deterministic and controlled—agents cannot bypass security constraints even through creative prompting. +*Security by design*: MCP servers enforce policies at the tool level, programmatically preventing prompt injection, SQL injection, and other agent-based attacks. Policy enforcement is deterministic and controlled—agents cannot bypass security constraints even through creative prompting. -**Unified authorization**:: All components use OIDC-based authentication with an "on-behalf-of" authorization model. When a user invokes an agent, the agent inherits the intersection of its own permissions and the user's permissions, ensuring proper data access scoping. +*Unified authorization*: All components use OIDC-based authentication with an "on-behalf-of" authorization model. When a user invokes an agent, the agent inherits the intersection of its own permissions and the user's permissions, ensuring proper data access scoping. -**Complete observability**:: ADP provides two levels of inspection: execution logs (transcripts) capture every agent action with 100% sampling using OpenTelemetry standards, while real-time debugging tools allow inspection of individual MCP server calls. Traces span across services and go as deep as needed—down to individual tool invocations with full timing data. View detailed agent actions in Redpanda Console and replay data for agent evaluations. +*Complete observability*: Redpanda ADP provides two levels of inspection: execution logs (transcripts) capture every agent action with 100% sampling using OpenTelemetry standards, while real-time debugging tools allow inspection of individual MCP server calls. Traces span across services and go as deep as needed—down to individual tool invocations with full timing data. View detailed agent actions in Redpanda Console and replay data for agent evaluations. -**Compliance and audit**:: For industries requiring multi-year audit trails, ADP records every agent action and data source used in decision-making. Execution logs are stored in Redpanda topics and can be materialized to Iceberg tables for long-term retention and analysis. +*Compliance and audit*: For industries requiring multi-year audit trails, Redpanda ADP records every agent action and data source used in decision-making. Execution logs are stored in Redpanda topics and can be materialized to Iceberg tables for long-term retention and analysis. -=== ADP deployment model +=== Redpanda ADP deployment model -ADP is primarily deployed using the <> model, where: +Redpanda ADP is deployed using the <> model, where: * The **control plane** (managed by Redpanda) handles provisioning, monitoring, and policy management -* The **data plane** (deployed in your cloud account) runs the ADP components and Redpanda cluster +* The **data plane** (deployed in your cloud account) runs the Redpanda ADP components and cluster * All your data remains in your infrastructure, providing maximum security and data sovereignty -ADP is built on open standards and protocols, allowing you to pick and choose components that fit your needs. Integrate with existing agent frameworks, data processing systems, or custom code—all components use standardized protocols for seamless interoperability. +Redpanda ADP is built on open standards and protocols, allowing you to pick and choose components that fit your needs. Integrate with existing agent frameworks, data processing systems, or custom code. All components use standardized protocols for seamless interoperability. === Use cases -Organizations use ADP to: +Organizations can use Redpanda ADP to: -* **Monitor manufacturing and operations**: Deploy multi-agent systems that analyze factory machine telemetry in real-time, detect anomalies, search equipment manuals, and create maintenance tickets automatically. Use data aggregation patterns (like tumbling windows) to process high-volume sensor data before sending insights to agents. -* **Extend enterprise productivity tools**: Integrate Microsoft Copilot or other workplace agents with internal data sources and systems that are otherwise inaccessible -* **Automate operational workflows**: Create specialized agents for building management, infrastructure monitoring, compliance reporting, and other domain-specific tasks +* *Automate operational workflows*: Create specialized agents for building management, infrastructure monitoring, compliance reporting, and other domain-specific tasks +* *Monitor manufacturing and operations*: Deploy multi-agent systems that analyze factory machine telemetry in real-time, detect anomalies, search equipment manuals, and create maintenance tickets automatically. Use data aggregation patterns (like tumbling windows) to process high-volume sensor data before sending insights to agents. +* *Extend enterprise productivity tools*: Integrate Microsoft Copilot or other workplace agents with internal data sources and systems that are otherwise inaccessible For details about building agents and MCP servers, see xref:ai-agents:index.adoc[]. -== Redpanda Cloud cluster types +== Redpanda Cloud deployment options -ADP and Redpanda Cloud applications are supported by three fully-managed deployment options. For ADP deployments, <> is the primary model, providing the security and data sovereignty required for enterprise agent platforms. For streaming applications, all three options are available: +Redpanda Cloud applications are supported by three fully-managed deployment options: * **<>**: Fastest way to get started with automatic scaling * **<>**: Production clusters in Redpanda's cloud with enhanced isolation @@ -73,16 +71,16 @@ ADP and Redpanda Cloud applications are supported by three fully-managed deploym | Production clusters requiring cloud hosting, higher throughput, and extra isolation | Production clusters requiring data sovereignty, the highest throughput, and added security -| *ADP support* -| Development and testing -| Development and testing -| Production (primary deployment model) - | *Deployment* | Redpanda's cloud (AWS/GCP) | Redpanda's cloud (AWS/Azure/GCP) | Your cloud account (AWS/Azure/GCP) +| *Redpanda ADP* +| ✗ +| ✗ +| ✓ + | *Tenancy* | Multi-tenant | Single-tenant @@ -202,7 +200,7 @@ Redpanda creates a cloud organization for you and sends you a welcome email. === Bring Your Own Cloud (BYOC) -BYOC is the primary deployment model for the Agent Development Platform (ADP). With BYOC clusters, the Redpanda data plane (including ADP components and Redpanda brokers) deploys into your existing VPC or VNet, ensuring all data remains in your environment. +With BYOC clusters, the Redpanda data plane (including Redpanda ADP components and Redpanda brokers) deploys into your existing VPC or VNet, ensuring all data remains in your environment. With BYOC clusters, you deploy the Redpanda glossterm:data plane[] into your existing VPC (for AWS and GCP) or VNet (for Azure), and all data is contained in your own environment. This provides an additional layer of security and isolation. (See xref:get-started:byoc-arch.adoc[].) Redpanda manages provisioning, monitoring, upgrades, and security policies, and it manages required resources in your VPC or VNet, including subnets (subnetworks in GCP), IAM roles, and object storage resources (for example, S3 buckets or Azure Storage accounts). @@ -213,6 +211,8 @@ With BYOVPC/BYOVNet clusters, you take full control of the networking lifecycle. The BYOC infrastructure that Redpanda manages should not be used to deploy any other workloads. +For details about the control plane - data plane framework in BYOC, see xref:get-started:byoc-arch.adoc[BYOC architecture]. + ==== Sign up for BYOC To start using BYOC, contact https://redpanda.com/try-redpanda?section=enterprise-trial[Redpanda sales^] to request a private offer with possible discounts. You are billed directly or through Google Cloud Marketplace or AWS Marketplace. @@ -237,7 +237,11 @@ Consider BYOC or Dedicated if you need more control over the deployment or if yo When you sign up for a Redpanda account, Redpanda creates an organization for you. Your organization contains all your Redpanda resources, including your clusters and networks. Within your organization, Redpanda creates a default resource group to contain your resources. You can rename this resource group, and you can create more resource groups. For example, you may want different resource groups for production and testing. -For details about the control plane - data plane framework in BYOC, see xref:get-started:byoc-arch.adoc[BYOC architecture]. +[TIP] +==== + +For more detailed information about the Redpanda platform, see xref:get-started:intro-to-events.adoc[] and xref:get-started:architecture.adoc[]. +==== == Shared responsibility model @@ -440,15 +444,14 @@ Features in beta are available for testing and feedback. They are not covered by The following features are currently in beta in Redpanda Cloud: -* Serverless on GCP * BYOVPC for AWS * BYOVNet for Azure * Secrets Management for BYOVPC on GCP and AWS -* xref:ai-agents:index.adoc[Agent Development Platform (ADP)] including AI agents, MCP servers, AI Gateway, and Catalog +* xref:ai-agents:index.adoc[Redpanda ADP] including AI agents, MCP servers, AI Gateway, and Transcripts * Several Redpanda Connect components == Next steps -* xref:ai-agents:index.adoc[Build AI agents with ADP] +* xref:ai-agents:index.adoc[Build AI agents with Redpanda ADP] * xref:manage:maintenance.adoc[Learn about upgrades and maintenance] * xref:get-started:cluster-types/serverless.adoc[Create a Serverless cluster] * xref:get-started:cluster-types/byoc/index.adoc[Create a BYOC cluster] From 9f8780ab2ba21205b81a32a160ad9526819e59bb Mon Sep 17 00:00:00 2001 From: micheleRP Date: Tue, 27 Jan 2026 23:18:57 -0700 Subject: [PATCH 04/11] minor edits --- modules/get-started/pages/cloud-overview.adoc | 26 +++++++------------ 1 file changed, 10 insertions(+), 16 deletions(-) diff --git a/modules/get-started/pages/cloud-overview.adoc b/modules/get-started/pages/cloud-overview.adoc index e54173c3f..3648a5f23 100644 --- a/modules/get-started/pages/cloud-overview.adoc +++ b/modules/get-started/pages/cloud-overview.adoc @@ -8,6 +8,10 @@ Redpanda Cloud is a complete data streaming and agentic data plane platform deli Redpanda ADP is an enterprise-grade infrastructure for building, deploying, and managing AI agents at scale. Redpanda ADP provides unified governance, observability, and security for agentic applications while leveraging Redpanda's streaming and analytical capabilities as the foundational data fabric. +Redpanda ADP is built on open standards and protocols, allowing you to pick and choose components that fit your needs. Integrate with existing agent frameworks, data processing systems, or custom code. All components use standardized protocols for seamless interoperability. + +NOTE: AI Gateway is supported on BYOC clusters running Redpanda version 25.3 and later. + === What is Redpanda ADP? Redpanda ADP combines multiple components into a cohesive platform built on open standards for maximum interoperability: @@ -17,28 +21,18 @@ Redpanda ADP combines multiple components into a cohesive platform built on open * **AI Gateway**: Manage LLM provider access with cost controls, rate limiting, intelligent routing, and failover support across multiple providers. //* **Catalog**: Maintain a centralized repository of agents, MCP servers, tools, and policies. Share components across teams and enforce organization-wide standards. -=== Enterprise capabilities +=== Enterprise capabilities for AI agents Redpanda ADP addresses critical enterprise requirements for AI agent deployments: -*Security by design*: MCP servers enforce policies at the tool level, programmatically preventing prompt injection, SQL injection, and other agent-based attacks. Policy enforcement is deterministic and controlled—agents cannot bypass security constraints even through creative prompting. +*Security by design*: MCP servers enforce policies at the tool level, programmatically preventing prompt injection, SQL injection, and other agent-based attacks. Policy enforcement is deterministic and controlled. Agents cannot bypass security constraints even through creative prompting. *Unified authorization*: All components use OIDC-based authentication with an "on-behalf-of" authorization model. When a user invokes an agent, the agent inherits the intersection of its own permissions and the user's permissions, ensuring proper data access scoping. -*Complete observability*: Redpanda ADP provides two levels of inspection: execution logs (transcripts) capture every agent action with 100% sampling using OpenTelemetry standards, while real-time debugging tools allow inspection of individual MCP server calls. Traces span across services and go as deep as needed—down to individual tool invocations with full timing data. View detailed agent actions in Redpanda Console and replay data for agent evaluations. +*Complete observability*: Redpanda ADP provides two levels of inspection: execution logs (transcripts) capture every agent action with 100% sampling using OpenTelemetry standards, while real-time debugging tools allow inspection of individual MCP server calls. Traces span across services and go as deep as needed, down to individual tool invocations with full timing data. View detailed agent actions in Redpanda Console and replay data for agent evaluations. *Compliance and audit*: For industries requiring multi-year audit trails, Redpanda ADP records every agent action and data source used in decision-making. Execution logs are stored in Redpanda topics and can be materialized to Iceberg tables for long-term retention and analysis. -=== Redpanda ADP deployment model - -Redpanda ADP is deployed using the <> model, where: - -* The **control plane** (managed by Redpanda) handles provisioning, monitoring, and policy management -* The **data plane** (deployed in your cloud account) runs the Redpanda ADP components and cluster -* All your data remains in your infrastructure, providing maximum security and data sovereignty - -Redpanda ADP is built on open standards and protocols, allowing you to pick and choose components that fit your needs. Integrate with existing agent frameworks, data processing systems, or custom code. All components use standardized protocols for seamless interoperability. - === Use cases Organizations can use Redpanda ADP to: @@ -47,7 +41,7 @@ Organizations can use Redpanda ADP to: * *Monitor manufacturing and operations*: Deploy multi-agent systems that analyze factory machine telemetry in real-time, detect anomalies, search equipment manuals, and create maintenance tickets automatically. Use data aggregation patterns (like tumbling windows) to process high-volume sensor data before sending insights to agents. * *Extend enterprise productivity tools*: Integrate Microsoft Copilot or other workplace agents with internal data sources and systems that are otherwise inaccessible -For details about building agents and MCP servers, see xref:ai-agents:index.adoc[]. +See also: xref:ai-agents:index.adoc[]. == Redpanda Cloud deployment options @@ -175,8 +169,7 @@ include::get-started:partial$get-started-serverless.adoc[] === Dedicated -With Dedicated clusters, you host your data on Redpanda Cloud resources (AWS, GCP, or Azure), and Redpanda handles provisioning, operations, and maintenance. Dedicated clusters are single-tenant deployments that support private networking (for example, VPC peering to talk over private IPs) for better data isolation. -When you create a Dedicated cluster, you select the supported xref:reference:tiers/dedicated-tiers.adoc[tier] that meets your compute and storage needs. +With Dedicated clusters, you host your data on Redpanda Cloud resources (AWS, GCP, or Azure), and Redpanda handles provisioning, operations, and maintenance. When you create a Dedicated cluster, you select the supported xref:reference:tiers/dedicated-tiers.adoc[tier] that meets your compute and storage needs. ==== Sign up for Dedicated @@ -228,6 +221,7 @@ Serverless clusters are a good fit for the following use cases: Consider BYOC or Dedicated if you need more control over the deployment or if you have workloads with consistently-high throughput. BYOC and Dedicated clusters offer the following features: +* Redpanda Agentic Data Plane (ADP): BYOC only * Multiple availability zones (AZs). A multi-AZ cluster provides higher resiliency in the event of a failure in one of the zones. * Role-based access control (RBAC) in the data plane * Kafka Connect From 3132fac17041311ecf09c11a71582e80c416172b Mon Sep 17 00:00:00 2001 From: micheleRP Date: Wed, 28 Jan 2026 13:58:32 -0700 Subject: [PATCH 05/11] minor edit --- modules/get-started/pages/cloud-overview.adoc | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/modules/get-started/pages/cloud-overview.adoc b/modules/get-started/pages/cloud-overview.adoc index 3648a5f23..e99d0502b 100644 --- a/modules/get-started/pages/cloud-overview.adoc +++ b/modules/get-started/pages/cloud-overview.adoc @@ -8,13 +8,9 @@ Redpanda Cloud is a complete data streaming and agentic data plane platform deli Redpanda ADP is an enterprise-grade infrastructure for building, deploying, and managing AI agents at scale. Redpanda ADP provides unified governance, observability, and security for agentic applications while leveraging Redpanda's streaming and analytical capabilities as the foundational data fabric. -Redpanda ADP is built on open standards and protocols, allowing you to pick and choose components that fit your needs. Integrate with existing agent frameworks, data processing systems, or custom code. All components use standardized protocols for seamless interoperability. - NOTE: AI Gateway is supported on BYOC clusters running Redpanda version 25.3 and later. -=== What is Redpanda ADP? - -Redpanda ADP combines multiple components into a cohesive platform built on open standards for maximum interoperability: +Redpanda ADP is built on open standards and protocols, allowing you to pick and choose components that fit your needs. Integrate with existing agent frameworks, data processing systems, or custom code. * **AI agents**: Deploy declarative agents or bring your own agent frameworks (LangChain, LlamaIndex, and others). Build multi-agent systems where specialized sub-agents handle specific responsibilities, following single-responsibility principles. * **MCP servers**: Build lightweight data and action interfaces using a low-code framework based on xref:develop:connect/about.adoc[Redpanda Connect]. Connect to hundreds of data sources (databases, cloud storage, APIs) and enforce fine-grained policies that programmatically prevent prompt injection and SQL injection attacks. MCP servers are extremely lightweight—run dozens on minimal resources—with OIDC-based access control and real-time debugging capabilities. From 8329532ee139757472af70c0292692a14c0e70c8 Mon Sep 17 00:00:00 2001 From: micheleRP Date: Wed, 28 Jan 2026 17:52:54 -0700 Subject: [PATCH 06/11] minor edit --- modules/get-started/pages/cloud-overview.adoc | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/modules/get-started/pages/cloud-overview.adoc b/modules/get-started/pages/cloud-overview.adoc index e99d0502b..3186ec408 100644 --- a/modules/get-started/pages/cloud-overview.adoc +++ b/modules/get-started/pages/cloud-overview.adoc @@ -8,7 +8,7 @@ Redpanda Cloud is a complete data streaming and agentic data plane platform deli Redpanda ADP is an enterprise-grade infrastructure for building, deploying, and managing AI agents at scale. Redpanda ADP provides unified governance, observability, and security for agentic applications while leveraging Redpanda's streaming and analytical capabilities as the foundational data fabric. -NOTE: AI Gateway is supported on BYOC clusters running Redpanda version 25.3 and later. +NOTE: The Agentic Data Plane is supported on BYOC clusters running Redpanda version 25.3 and later. Redpanda ADP is built on open standards and protocols, allowing you to pick and choose components that fit your needs. Integrate with existing agent frameworks, data processing systems, or custom code. From 553a4b65f8631e5019fa274f2071d76ec5b7faae Mon Sep 17 00:00:00 2001 From: micheleRP Date: Thu, 29 Jan 2026 10:35:31 -0700 Subject: [PATCH 07/11] AWS only & what's new blurb # Conflicts: # modules/get-started/pages/whats-new-cloud.adoc --- modules/get-started/pages/cloud-overview.adoc | 4 ++-- modules/get-started/pages/whats-new-cloud.adoc | 12 ++++++++++++ 2 files changed, 14 insertions(+), 2 deletions(-) diff --git a/modules/get-started/pages/cloud-overview.adoc b/modules/get-started/pages/cloud-overview.adoc index 3186ec408..f406c8218 100644 --- a/modules/get-started/pages/cloud-overview.adoc +++ b/modules/get-started/pages/cloud-overview.adoc @@ -8,9 +8,9 @@ Redpanda Cloud is a complete data streaming and agentic data plane platform deli Redpanda ADP is an enterprise-grade infrastructure for building, deploying, and managing AI agents at scale. Redpanda ADP provides unified governance, observability, and security for agentic applications while leveraging Redpanda's streaming and analytical capabilities as the foundational data fabric. -NOTE: The Agentic Data Plane is supported on BYOC clusters running Redpanda version 25.3 and later. +NOTE: The Agentic Data Plane is supported on BYOC clusters running with AWS and Redpanda version 25.3 and later. -Redpanda ADP is built on open standards and protocols, allowing you to pick and choose components that fit your needs. Integrate with existing agent frameworks, data processing systems, or custom code. +Redpanda ADP is built on open standards and protocols, allowing you to pick and choose components that fit your needs. Integrate with existing agent frameworks, data processing systems, or custom code. It includes the following key components: * **AI agents**: Deploy declarative agents or bring your own agent frameworks (LangChain, LlamaIndex, and others). Build multi-agent systems where specialized sub-agents handle specific responsibilities, following single-responsibility principles. * **MCP servers**: Build lightweight data and action interfaces using a low-code framework based on xref:develop:connect/about.adoc[Redpanda Connect]. Connect to hundreds of data sources (databases, cloud storage, APIs) and enforce fine-grained policies that programmatically prevent prompt injection and SQL injection attacks. MCP servers are extremely lightweight—run dozens on minimal resources—with OIDC-based access control and real-time debugging capabilities. diff --git a/modules/get-started/pages/whats-new-cloud.adoc b/modules/get-started/pages/whats-new-cloud.adoc index 1231b4d32..776c149f6 100644 --- a/modules/get-started/pages/whats-new-cloud.adoc +++ b/modules/get-started/pages/whats-new-cloud.adoc @@ -8,6 +8,18 @@ This page lists new features added to Redpanda Cloud. == February 2026 +=== Agentic Data Plane (ADP) + +Redpanda ADP is an enterprise-grade infrastructure for building, deploying, and managing AI agents at scale. Redpanda ADP provides unified governance, observability, and security for agentic applications while leveraging Redpanda's streaming and analytical capabilities as the foundational data fabric. + +NOTE: The Agentic Data Plane is supported on BYOC clusters running with AWS and Redpanda version 25.3 and later. + +Redpanda ADP is built on open standards and protocols, allowing you to pick and choose components that fit your needs. Integrate with existing agent frameworks, data processing systems, or custom code. It includes the following key components: + +* **AI agents**: Deploy declarative agents or bring your own agent frameworks (LangChain, LlamaIndex, and others). Build multi-agent systems where specialized sub-agents handle specific responsibilities, following single-responsibility principles. +* **MCP servers**: Build lightweight data and action interfaces using a low-code framework based on xref:develop:connect/about.adoc[Redpanda Connect]. Connect to hundreds of data sources (databases, cloud storage, APIs) and enforce fine-grained policies that programmatically prevent prompt injection and SQL injection attacks. MCP servers are extremely lightweight—run dozens on minimal resources—with OIDC-based access control and real-time debugging capabilities. +* **AI Gateway**: Manage LLM provider access with cost controls, rate limiting, intelligent routing, and failover support across multiple providers. + === Serverless on AWS: GA xref:get-started:cluster-types/serverless.adoc[Serverless] on AWS is now generally available (GA). This release includes private networking with AWS PrivateLink. You can use the Cloud Console, the Cloud API, or the Redpanda Terraform provider to create and manage Serverless private links. Serverless is the easiest and fastest way to begin streaming data with Redpanda. From 7a08929d4b1af070f90214bb07400e56f8a54d61 Mon Sep 17 00:00:00 2001 From: micheleRP Date: Wed, 4 Feb 2026 17:57:18 -0700 Subject: [PATCH 08/11] incorporate review feedback + add glossary terms --- modules/get-started/pages/cloud-overview.adoc | 10 +++++----- modules/get-started/pages/whats-new-cloud.adoc | 6 +++--- 2 files changed, 8 insertions(+), 8 deletions(-) diff --git a/modules/get-started/pages/cloud-overview.adoc b/modules/get-started/pages/cloud-overview.adoc index f406c8218..107c8e01e 100644 --- a/modules/get-started/pages/cloud-overview.adoc +++ b/modules/get-started/pages/cloud-overview.adoc @@ -6,15 +6,15 @@ Redpanda Cloud is a complete data streaming and agentic data plane platform deli == Redpanda Agentic Data Plane (ADP) -Redpanda ADP is an enterprise-grade infrastructure for building, deploying, and managing AI agents at scale. Redpanda ADP provides unified governance, observability, and security for agentic applications while leveraging Redpanda's streaming and analytical capabilities as the foundational data fabric. +Redpanda ADP is an enterprise-grade infrastructure for building, deploying, and managing AI agents at scale. Redpanda ADP provides unified governance, observability, and security for agentic applications while leveraging Redpanda's streaming and analytical foundation. NOTE: The Agentic Data Plane is supported on BYOC clusters running with AWS and Redpanda version 25.3 and later. Redpanda ADP is built on open standards and protocols, allowing you to pick and choose components that fit your needs. Integrate with existing agent frameworks, data processing systems, or custom code. It includes the following key components: -* **AI agents**: Deploy declarative agents or bring your own agent frameworks (LangChain, LlamaIndex, and others). Build multi-agent systems where specialized sub-agents handle specific responsibilities, following single-responsibility principles. -* **MCP servers**: Build lightweight data and action interfaces using a low-code framework based on xref:develop:connect/about.adoc[Redpanda Connect]. Connect to hundreds of data sources (databases, cloud storage, APIs) and enforce fine-grained policies that programmatically prevent prompt injection and SQL injection attacks. MCP servers are extremely lightweight—run dozens on minimal resources—with OIDC-based access control and real-time debugging capabilities. -* **AI Gateway**: Manage LLM provider access with cost controls, rate limiting, intelligent routing, and failover support across multiple providers. +* **glossterm:AI agent[,AI agents]**: Deploy declarative agents or bring your own agent frameworks (such as LangChain or LlamaIndex). Build multi-agent systems where specialized glossterm:subagent[,sub-agents] handle specific responsibilities, following single-responsibility principles. +* **glossterm:MCP server[,MCP servers]**: Build lightweight data and action interfaces using xref:develop:connect/about.adoc[Redpanda Connect] or your own hosted MCP servers. Connect to hundreds of data sources (databases, cloud storage, APIs) and enforce fine-grained policies that programmatically prevent prompt injection and SQL injection attacks. MCP servers are extremely lightweight, with OIDC-based access control and real-time debugging capabilities. +* **AI Gateway**: Manage large language model (LLM) provider access with cost controls, rate limiting, intelligent routing, and failover support across multiple providers. //* **Catalog**: Maintain a centralized repository of agents, MCP servers, tools, and policies. Share components across teams and enforce organization-wide standards. === Enterprise capabilities for AI agents @@ -25,7 +25,7 @@ Redpanda ADP addresses critical enterprise requirements for AI agent deployments *Unified authorization*: All components use OIDC-based authentication with an "on-behalf-of" authorization model. When a user invokes an agent, the agent inherits the intersection of its own permissions and the user's permissions, ensuring proper data access scoping. -*Complete observability*: Redpanda ADP provides two levels of inspection: execution logs (transcripts) capture every agent action with 100% sampling using OpenTelemetry standards, while real-time debugging tools allow inspection of individual MCP server calls. Traces span across services and go as deep as needed, down to individual tool invocations with full timing data. View detailed agent actions in Redpanda Console and replay data for agent evaluations. +*Complete observability*: Redpanda ADP provides two levels of inspection: execution logs (glossterm:transcript[,transcripts]) capture every agent action with 100% sampling using OpenTelemetry standards, while real-time debugging tools allow inspection of individual MCP server calls. Traces span across services and go as deep as needed, down to individual tool invocations with full timing data. View detailed agent actions in Redpanda Console and replay data for agent evaluations. *Compliance and audit*: For industries requiring multi-year audit trails, Redpanda ADP records every agent action and data source used in decision-making. Execution logs are stored in Redpanda topics and can be materialized to Iceberg tables for long-term retention and analysis. diff --git a/modules/get-started/pages/whats-new-cloud.adoc b/modules/get-started/pages/whats-new-cloud.adoc index 776c149f6..496c6a447 100644 --- a/modules/get-started/pages/whats-new-cloud.adoc +++ b/modules/get-started/pages/whats-new-cloud.adoc @@ -16,9 +16,9 @@ NOTE: The Agentic Data Plane is supported on BYOC clusters running with AWS and Redpanda ADP is built on open standards and protocols, allowing you to pick and choose components that fit your needs. Integrate with existing agent frameworks, data processing systems, or custom code. It includes the following key components: -* **AI agents**: Deploy declarative agents or bring your own agent frameworks (LangChain, LlamaIndex, and others). Build multi-agent systems where specialized sub-agents handle specific responsibilities, following single-responsibility principles. -* **MCP servers**: Build lightweight data and action interfaces using a low-code framework based on xref:develop:connect/about.adoc[Redpanda Connect]. Connect to hundreds of data sources (databases, cloud storage, APIs) and enforce fine-grained policies that programmatically prevent prompt injection and SQL injection attacks. MCP servers are extremely lightweight—run dozens on minimal resources—with OIDC-based access control and real-time debugging capabilities. -* **AI Gateway**: Manage LLM provider access with cost controls, rate limiting, intelligent routing, and failover support across multiple providers. +* **glossterm:AI agent[,AI agents]**: Deploy declarative agents or bring your own agent frameworks (LangChain, LlamaIndex, and others). Build multi-agent systems where specialized glossterm:subagent[,sub-agents] handle specific responsibilities, following single-responsibility principles. +* **glossterm:MCP server[,MCP servers]**: Build lightweight data and action interfaces using a low-code framework based on xref:develop:connect/about.adoc[Redpanda Connect]. Connect to hundreds of data sources (databases, cloud storage, APIs) and enforce fine-grained policies that programmatically prevent prompt injection and SQL injection attacks. MCP servers are extremely lightweight—run dozens on minimal resources—with OIDC-based access control and real-time debugging capabilities. +* **AI Gateway**: Manage large language model (LLM) provider access with cost controls, rate limiting, intelligent routing, and failover support across multiple providers. === Serverless on AWS: GA From 7118594e6bc78476a1224cb6d4ad20e2525eb7f4 Mon Sep 17 00:00:00 2001 From: micheleRP Date: Sat, 7 Feb 2026 15:47:30 -0700 Subject: [PATCH 09/11] improved messaging from Alex + new ADP overview --- modules/ROOT/nav.adoc | 1 + modules/ai-agents/pages/adp-overview.adoc | 74 ++++++++++++++++++ modules/ai-agents/pages/index.adoc | 4 +- modules/ai-agents/pages/overview.adoc | 76 +++++++++++++++++++ modules/get-started/pages/cloud-overview.adoc | 36 ++------- .../get-started/pages/whats-new-cloud.adoc | 10 +-- 6 files changed, 164 insertions(+), 37 deletions(-) create mode 100644 modules/ai-agents/pages/adp-overview.adoc create mode 100644 modules/ai-agents/pages/overview.adoc diff --git a/modules/ROOT/nav.adoc b/modules/ROOT/nav.adoc index 422c6f540..0de25b417 100644 --- a/modules/ROOT/nav.adoc +++ b/modules/ROOT/nav.adoc @@ -24,6 +24,7 @@ ** xref:get-started:cluster-types/create-dedicated-cloud-cluster.adoc[] * xref:ai-agents:index.adoc[Agentic AI] +** xref:ai-agents:adp-overview.adoc[ADP Overview] ** xref:ai-agents:mcp/index.adoc[MCP] *** xref:ai-agents:mcp/overview.adoc[MCP Overview] *** xref:ai-agents:mcp/remote/index.adoc[Remote MCP] diff --git a/modules/ai-agents/pages/adp-overview.adoc b/modules/ai-agents/pages/adp-overview.adoc new file mode 100644 index 000000000..799d9bf81 --- /dev/null +++ b/modules/ai-agents/pages/adp-overview.adoc @@ -0,0 +1,74 @@ += Redpanda Agentic Data Plane Overview +:description: Enterprise-grade infrastructure for building, deploying, and governing AI agents at scale with compliance-grade audit trails. +:page-topic-type: overview +:page-categories: AI, Agentic AI +:personas: evaluator, ai_agent_developer, platform_admin +:learning-objective-1: Identify the key components of Redpanda ADP and their purposes +:learning-objective-2: Describe how each component addresses enterprise governance and reliability requirements +:learning-objective-3: Determine whether Redpanda ADP fits your organization's requirements for AI agent deployment + +glossterm:AI agent[,AI agents] are moving from demos to production. Enterprises need governance, reliability, and cost control to deploy them safely. Redpanda Agentic Data Plane (ADP) closes those gaps by combining a streaming-native immutable log, 300+ proven data connectors, and declarative agent definitions into a unified platform with built-in compliance-grade audit trails. + +After reading this page, you will be able to: + +* [ ] {learning-objective-1} +* [ ] {learning-objective-2} +* [ ] {learning-objective-3} + +NOTE: The Agentic Data Plane is supported on BYOC clusters running with AWS and Redpanda version 25.3 and later. + +== AI Agents + +Instead of writing Python or JavaScript, you declare the agent behavior you want and Redpanda handles execution and orchestration. You define behaviors in YAML, orchestrate multiple specialized glossterm:subagent[,sub-agents], or bring your own frameworks like LangChain or LlamaIndex. + +What makes this practical at scale is xref:develop:connect/about.adoc[Redpanda Connect]. More than 300 connectors with built-in filtering, enrichment, and routing give declarative definitions real power. Upcoming templates will provide default behaviors for common domains such as customer success, legal, and finance. + +The result is faster time-to-production, lower maintenance (declarative definitions instead of imperative code), and organizational consistency across teams. + +== MCP Servers + +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: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. + +With 300+ connectors out of the box 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. + +== Transcripts + +Every agent action is recorded in an end-to-end execution log. A single glossterm:transcript[] can span multiple agents, tools, and models, covering interactions that last minutes to days. + +Transcripts are the keystone of agent governance. They are built on Redpanda's immutable log with Raft consensus and TLA+ correctness proofs. No gaps, no tampering. For regulated industries that require multi-year audit trails, this provides a compliance-grade record of every decision an agent makes and every data source it uses. + +Redpanda captures 100% of agent actions through OpenTelemetry standards, with end-to-end lineage across the entire execution chain. You can materialize execution logs to Iceberg tables for long-term retention and analysis, or replay them to evaluate and improve agent performance over time. + +== AI Gateway + +The AI Gateway manages LLM provider access with two priorities: keeping your application up and keeping costs under control. + +For high availability, the gateway provides provider-agnostic routing with intelligent failover. Your users don't care which provider serves a request. They care that the application stays up. For fiscal control, you get per-tenant budgets and rate limiting, so there are no runaway costs and no surprise bills. + +The gateway also supports tenancy modeling for teams, individuals, applications, and service accounts, giving you chargeback transparency for internal cost allocation. You can proxy both models and MCP gateways, centralizing compliance for all LLM interactions without locking into any single provider. + +== Enterprise governance + +Redpanda ADP addresses critical enterprise requirements across all components. + +*Security by design*:: MCP servers enforce policies at the tool level, programmatically preventing prompt injection, SQL injection, and other agent-based attacks. Policy enforcement is deterministic and controlled. Agents cannot bypass security constraints even through creative prompting. + +*Unified authorization*:: All components use OIDC-based authentication with an on-behalf-of authorization model. When a user invokes an agent, the agent inherits the intersection of its own permissions and the user's permissions. This ensures proper data access scoping. + +*Complete observability*:: Redpanda ADP provides two levels of inspection. Execution logs (transcripts) capture every agent action with 100% sampling using OpenTelemetry standards. Real-time debugging tools allow you to inspect individual MCP server calls down to individual tool invocations with full timing data. You can view detailed agent actions in glossterm:Redpanda Console[] and replay data for agent evaluations. + +*Compliance and audit*:: For industries requiring multi-year audit trails, Redpanda ADP records every agent action and data source used in decision-making. Execution logs are stored in Redpanda topics and can be materialized to Iceberg tables for long-term retention and analysis. + +== Use cases + +Organizations use Redpanda ADP to: + +* *Automate operational workflows*: Create specialized agents for building management, infrastructure monitoring, compliance reporting, and other domain-specific tasks. +* *Monitor manufacturing and operations*: Deploy multi-agent systems that analyze factory machine telemetry in real-time, detect anomalies, search equipment manuals, and create maintenance tickets automatically. +* *Extend enterprise productivity tools*: Integrate Microsoft Copilot or other workplace agents with internal data sources and systems that are otherwise inaccessible. + +== Next steps + +* xref:ai-agents:mcp/overview.adoc[] diff --git a/modules/ai-agents/pages/index.adoc b/modules/ai-agents/pages/index.adoc index 9ac867a96..d4af999fc 100644 --- a/modules/ai-agents/pages/index.adoc +++ b/modules/ai-agents/pages/index.adoc @@ -3,6 +3,8 @@ :page-layout: index :page-aliases: develop:agents/about.adoc, develop:ai-agents/about.adoc -AI agents are configurable assistants that autonomously perform specialist tasks by leveraging large language models (LLMs) and connecting to external data sources and tools. +glossterm:AI agent[,AI agents] are configurable assistants that autonomously perform specialist tasks by leveraging large language models (LLMs) and connecting to external data sources and tools. + +Redpanda's xref:ai-agents:adp-overview.adoc[Agentic Data Plane (ADP)] provides enterprise-grade infrastructure for building, deploying, and governing AI agents at scale with four key components that deliver enterprise governance, cost controls, and compliance-grade audit trails. Redpanda Cloud provides two complementary Model Context Protocol (MCP) options to help you build AI agents. diff --git a/modules/ai-agents/pages/overview.adoc b/modules/ai-agents/pages/overview.adoc new file mode 100644 index 000000000..08c4a9fe0 --- /dev/null +++ b/modules/ai-agents/pages/overview.adoc @@ -0,0 +1,76 @@ += Redpanda Agentic Data Plane Overview +:description: Enterprise-grade infrastructure for building, deploying, and governing AI agents at scale with compliance-grade audit trails. +:page-topic-type: overview +:page-categories: AI, Agentic AI +:personas: evaluator, ai_agent_developer, platform_admin +:learning-objective-1: Identify the four key components of Redpanda ADP and their purposes +:learning-objective-2: Describe how each component addresses enterprise governance and reliability requirements +:learning-objective-3: Determine whether Redpanda ADP fits your organization's requirements for AI agent deployment + +glossterm:AI agent[,AI agents] are moving from demos to production. Enterprises need governance, reliability, and cost control to deploy them safely. Redpanda Agentic Data Plane (ADP) closes those gaps by combining a streaming-native immutable log, 300+ proven data connectors, and declarative agent definitions into a unified platform with built-in compliance-grade audit trails. + +After reading this page, you will be able to: + +* [ ] {learning-objective-1} +* [ ] {learning-objective-2} +* [ ] {learning-objective-3} + +NOTE: The Agentic Data Plane is supported on BYOC clusters running with AWS and Redpanda version 25.3 and later. + +== AI Agents + +Instead of writing Python or JavaScript, you declare the agent behavior you want and Redpanda handles execution and orchestration. You define behaviors in YAML, orchestrate multiple specialized glossterm:subagent[,sub-agents], or bring your own frameworks like LangChain or LlamaIndex. + +What makes this practical at scale is xref:develop:connect/about.adoc[Redpanda Connect]. More than 300 connectors with built-in filtering, enrichment, and routing give declarative definitions real power. Upcoming templates will provide default behaviors for common domains such as customer success, legal, and finance. + +The result is faster time-to-production, lower maintenance (declarative definitions instead of imperative code), and organizational consistency across teams. + +== MCP Servers + +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: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. + +With 300+ connectors out of the box 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. + +== Transcripts + +Every agent action is recorded in an end-to-end execution log. A single glossterm:transcript[] can span multiple agents, tools, and models, covering interactions that last minutes to days. + +Transcripts are the keystone of agent governance. They are built on Redpanda's immutable log with Raft consensus and TLA+ correctness proofs. No gaps, no tampering. For regulated industries that require multi-year audit trails, this provides a compliance-grade record of every decision an agent makes and every data source it uses. + +Redpanda captures 100% of agent actions through OpenTelemetry standards, with end-to-end lineage across the entire execution chain. You can materialize execution logs to Iceberg tables for long-term retention and analysis, or replay them to evaluate and improve agent performance over time. + +== AI Gateway + +The AI Gateway manages LLM provider access with two priorities: keeping your application up and keeping costs under control. + +For high availability, the gateway provides provider-agnostic routing with intelligent failover. Your users don't care which provider serves a request. They care that the application stays up. For fiscal control, you get per-tenant budgets and rate limiting, so there are no runaway costs and no surprise bills. + +The gateway also supports tenancy modeling for teams, individuals, applications, and service accounts, giving you chargeback transparency for internal cost allocation. You can proxy both models and MCP gateways, centralizing compliance for all LLM interactions without locking into any single provider. + +== Enterprise governance + +Redpanda ADP addresses critical enterprise requirements across all components. + +*Security by design*:: MCP servers enforce policies at the tool level, programmatically preventing prompt injection, SQL injection, and other agent-based attacks. Policy enforcement is deterministic and controlled. Agents cannot bypass security constraints even through creative prompting. + +*Unified authorization*:: All components use OIDC-based authentication with an on-behalf-of authorization model. When a user invokes an agent, the agent inherits the intersection of its own permissions and the user's permissions. This ensures proper data access scoping. + +*Complete observability*:: Redpanda ADP provides two levels of inspection. Execution logs (transcripts) capture every agent action with 100% sampling using OpenTelemetry standards. Real-time debugging tools allow you to inspect individual MCP server calls down to individual tool invocations with full timing data. You can view detailed agent actions in glossterm:Redpanda Console[] and replay data for agent evaluations. + +*Compliance and audit*:: For industries requiring multi-year audit trails, Redpanda ADP records every agent action and data source used in decision-making. Execution logs are stored in Redpanda topics and can be materialized to Iceberg tables for long-term retention and analysis. + +== Use cases + +Organizations use Redpanda ADP to: + +* *Automate operational workflows*: Create specialized agents for building management, infrastructure monitoring, compliance reporting, and other domain-specific tasks. +* *Monitor manufacturing and operations*: Deploy multi-agent systems that analyze factory machine telemetry in real-time, detect anomalies, search equipment manuals, and create maintenance tickets automatically. +* *Extend enterprise productivity tools*: Integrate Microsoft Copilot or other workplace agents with internal data sources and systems that are otherwise inaccessible. + +== Next steps + +* xref:ai-agents:mcp/overview.adoc[] +* xref:ai-agents:mcp/remote/quickstart.adoc[] +* xref:ai-agents:mcp/local/quickstart.adoc[] diff --git a/modules/get-started/pages/cloud-overview.adoc b/modules/get-started/pages/cloud-overview.adoc index 107c8e01e..6602ce9f7 100644 --- a/modules/get-started/pages/cloud-overview.adoc +++ b/modules/get-started/pages/cloud-overview.adoc @@ -6,38 +6,18 @@ Redpanda Cloud is a complete data streaming and agentic data plane platform deli == Redpanda Agentic Data Plane (ADP) -Redpanda ADP is an enterprise-grade infrastructure for building, deploying, and managing AI agents at scale. Redpanda ADP provides unified governance, observability, and security for agentic applications while leveraging Redpanda's streaming and analytical foundation. +Redpanda Agentic Data Plane (ADP) is enterprise-grade infrastructure for building, deploying, and governing glossterm:AI agent[,AI agents] at scale. It combines Redpanda's streaming-native immutable log, 300+ proven data connectors, and declarative agent definitions into a unified platform with built-in governance, cost controls, and compliance-grade audit trails. -NOTE: The Agentic Data Plane is supported on BYOC clusters running with AWS and Redpanda version 25.3 and later. - -Redpanda ADP is built on open standards and protocols, allowing you to pick and choose components that fit your needs. Integrate with existing agent frameworks, data processing systems, or custom code. It includes the following key components: - -* **glossterm:AI agent[,AI agents]**: Deploy declarative agents or bring your own agent frameworks (such as LangChain or LlamaIndex). Build multi-agent systems where specialized glossterm:subagent[,sub-agents] handle specific responsibilities, following single-responsibility principles. -* **glossterm:MCP server[,MCP servers]**: Build lightweight data and action interfaces using xref:develop:connect/about.adoc[Redpanda Connect] or your own hosted MCP servers. Connect to hundreds of data sources (databases, cloud storage, APIs) and enforce fine-grained policies that programmatically prevent prompt injection and SQL injection attacks. MCP servers are extremely lightweight, with OIDC-based access control and real-time debugging capabilities. -* **AI Gateway**: Manage large language model (LLM) provider access with cost controls, rate limiting, intelligent routing, and failover support across multiple providers. -//* **Catalog**: Maintain a centralized repository of agents, MCP servers, tools, and policies. Share components across teams and enforce organization-wide standards. - -=== Enterprise capabilities for AI agents - -Redpanda ADP addresses critical enterprise requirements for AI agent deployments: - -*Security by design*: MCP servers enforce policies at the tool level, programmatically preventing prompt injection, SQL injection, and other agent-based attacks. Policy enforcement is deterministic and controlled. Agents cannot bypass security constraints even through creative prompting. +Redpanda ADP includes the following key components: -*Unified authorization*: All components use OIDC-based authentication with an "on-behalf-of" authorization model. When a user invokes an agent, the agent inherits the intersection of its own permissions and the user's permissions, ensuring proper data access scoping. +* *AI Agents*: Declare the behavior you want instead of writing code. Redpanda powers declarative definitions with 300+ connectors. +* *MCP Servers*: Translate agent intent into connections to your business systems using proven connectors, no glue code required. +* *Transcripts*: End-to-end execution records built on an immutable log with formal correctness guarantees. Transcripts are the keystone of agent governance. +* *AI Gateway*: High-availability model routing with fiscal controls and per-tenant cost attribution across LLM providers. -*Complete observability*: Redpanda ADP provides two levels of inspection: execution logs (glossterm:transcript[,transcripts]) capture every agent action with 100% sampling using OpenTelemetry standards, while real-time debugging tools allow inspection of individual MCP server calls. Traces span across services and go as deep as needed, down to individual tool invocations with full timing data. View detailed agent actions in Redpanda Console and replay data for agent evaluations. - -*Compliance and audit*: For industries requiring multi-year audit trails, Redpanda ADP records every agent action and data source used in decision-making. Execution logs are stored in Redpanda topics and can be materialized to Iceberg tables for long-term retention and analysis. - -=== Use cases - -Organizations can use Redpanda ADP to: - -* *Automate operational workflows*: Create specialized agents for building management, infrastructure monitoring, compliance reporting, and other domain-specific tasks -* *Monitor manufacturing and operations*: Deploy multi-agent systems that analyze factory machine telemetry in real-time, detect anomalies, search equipment manuals, and create maintenance tickets automatically. Use data aggregation patterns (like tumbling windows) to process high-volume sensor data before sending insights to agents. -* *Extend enterprise productivity tools*: Integrate Microsoft Copilot or other workplace agents with internal data sources and systems that are otherwise inaccessible +NOTE: The Agentic Data Plane is supported on BYOC clusters running with AWS and Redpanda version 25.3 and later. -See also: xref:ai-agents:index.adoc[]. +To learn what makes Redpanda's approach unique, see xref:ai-agents:adp-overview.adoc[]. == Redpanda Cloud deployment options diff --git a/modules/get-started/pages/whats-new-cloud.adoc b/modules/get-started/pages/whats-new-cloud.adoc index 496c6a447..c1174c9ef 100644 --- a/modules/get-started/pages/whats-new-cloud.adoc +++ b/modules/get-started/pages/whats-new-cloud.adoc @@ -10,15 +10,9 @@ This page lists new features added to Redpanda Cloud. === Agentic Data Plane (ADP) -Redpanda ADP is an enterprise-grade infrastructure for building, deploying, and managing AI agents at scale. Redpanda ADP provides unified governance, observability, and security for agentic applications while leveraging Redpanda's streaming and analytical capabilities as the foundational data fabric. +Redpanda Agentic Data Plane (ADP) provides enterprise-grade infrastructure for building, deploying, and governing AI agents at scale. Key capabilities include declarative agents, MCP servers backed by 300+ connectors, an AI Gateway with model failover and fiscal controls, and compliance-grade transcripts built on Redpanda's immutable log. Redpanda ADP is now available on BYOC clusters (AWS, Redpanda 25.3+). -NOTE: The Agentic Data Plane is supported on BYOC clusters running with AWS and Redpanda version 25.3 and later. - -Redpanda ADP is built on open standards and protocols, allowing you to pick and choose components that fit your needs. Integrate with existing agent frameworks, data processing systems, or custom code. It includes the following key components: - -* **glossterm:AI agent[,AI agents]**: Deploy declarative agents or bring your own agent frameworks (LangChain, LlamaIndex, and others). Build multi-agent systems where specialized glossterm:subagent[,sub-agents] handle specific responsibilities, following single-responsibility principles. -* **glossterm:MCP server[,MCP servers]**: Build lightweight data and action interfaces using a low-code framework based on xref:develop:connect/about.adoc[Redpanda Connect]. Connect to hundreds of data sources (databases, cloud storage, APIs) and enforce fine-grained policies that programmatically prevent prompt injection and SQL injection attacks. MCP servers are extremely lightweight—run dozens on minimal resources—with OIDC-based access control and real-time debugging capabilities. -* **AI Gateway**: Manage large language model (LLM) provider access with cost controls, rate limiting, intelligent routing, and failover support across multiple providers. +See xref:ai-agents:adp-overview.adoc[Agentic Data Plane Overview]. === Serverless on AWS: GA From ac0ec9d59694f85209be463274b328dc4a8a65bb Mon Sep 17 00:00:00 2001 From: micheleRP Date: Sat, 7 Feb 2026 21:29:53 -0700 Subject: [PATCH 10/11] delete original overview --- modules/ai-agents/pages/adp-overview.adoc | 4 +- modules/ai-agents/pages/overview.adoc | 76 ----------------------- 2 files changed, 2 insertions(+), 78 deletions(-) delete mode 100644 modules/ai-agents/pages/overview.adoc diff --git a/modules/ai-agents/pages/adp-overview.adoc b/modules/ai-agents/pages/adp-overview.adoc index 799d9bf81..7427b9817 100644 --- a/modules/ai-agents/pages/adp-overview.adoc +++ b/modules/ai-agents/pages/adp-overview.adoc @@ -7,7 +7,7 @@ :learning-objective-2: Describe how each component addresses enterprise governance and reliability requirements :learning-objective-3: Determine whether Redpanda ADP fits your organization's requirements for AI agent deployment -glossterm:AI agent[,AI agents] are moving from demos to production. Enterprises need governance, reliability, and cost control to deploy them safely. Redpanda Agentic Data Plane (ADP) closes those gaps by combining a streaming-native immutable log, 300+ proven data connectors, and declarative agent definitions into a unified platform with built-in compliance-grade audit trails. +glossterm:AI agent[,AI agents] are moving from demos to production. Enterprises need governance, reliability, and cost control to deploy them safely. Redpanda Agentic Data Plane (ADP) combine a streaming-native immutable log, 300+ proven data connectors, and declarative glossterm:AI agent[,AI agents] into a unified platform with built-in compliance-grade audit trails. After reading this page, you will be able to: @@ -31,7 +31,7 @@ glossterm:MCP server[,MCP servers] translate agent intent into connections to da 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: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. -With 300+ connectors out of the box 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 over 300 connectors out-of-the-box 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. == Transcripts diff --git a/modules/ai-agents/pages/overview.adoc b/modules/ai-agents/pages/overview.adoc deleted file mode 100644 index 08c4a9fe0..000000000 --- a/modules/ai-agents/pages/overview.adoc +++ /dev/null @@ -1,76 +0,0 @@ -= Redpanda Agentic Data Plane Overview -:description: Enterprise-grade infrastructure for building, deploying, and governing AI agents at scale with compliance-grade audit trails. -:page-topic-type: overview -:page-categories: AI, Agentic AI -:personas: evaluator, ai_agent_developer, platform_admin -:learning-objective-1: Identify the four key components of Redpanda ADP and their purposes -:learning-objective-2: Describe how each component addresses enterprise governance and reliability requirements -:learning-objective-3: Determine whether Redpanda ADP fits your organization's requirements for AI agent deployment - -glossterm:AI agent[,AI agents] are moving from demos to production. Enterprises need governance, reliability, and cost control to deploy them safely. Redpanda Agentic Data Plane (ADP) closes those gaps by combining a streaming-native immutable log, 300+ proven data connectors, and declarative agent definitions into a unified platform with built-in compliance-grade audit trails. - -After reading this page, you will be able to: - -* [ ] {learning-objective-1} -* [ ] {learning-objective-2} -* [ ] {learning-objective-3} - -NOTE: The Agentic Data Plane is supported on BYOC clusters running with AWS and Redpanda version 25.3 and later. - -== AI Agents - -Instead of writing Python or JavaScript, you declare the agent behavior you want and Redpanda handles execution and orchestration. You define behaviors in YAML, orchestrate multiple specialized glossterm:subagent[,sub-agents], or bring your own frameworks like LangChain or LlamaIndex. - -What makes this practical at scale is xref:develop:connect/about.adoc[Redpanda Connect]. More than 300 connectors with built-in filtering, enrichment, and routing give declarative definitions real power. Upcoming templates will provide default behaviors for common domains such as customer success, legal, and finance. - -The result is faster time-to-production, lower maintenance (declarative definitions instead of imperative code), and organizational consistency across teams. - -== MCP Servers - -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: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. - -With 300+ connectors out of the box 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. - -== Transcripts - -Every agent action is recorded in an end-to-end execution log. A single glossterm:transcript[] can span multiple agents, tools, and models, covering interactions that last minutes to days. - -Transcripts are the keystone of agent governance. They are built on Redpanda's immutable log with Raft consensus and TLA+ correctness proofs. No gaps, no tampering. For regulated industries that require multi-year audit trails, this provides a compliance-grade record of every decision an agent makes and every data source it uses. - -Redpanda captures 100% of agent actions through OpenTelemetry standards, with end-to-end lineage across the entire execution chain. You can materialize execution logs to Iceberg tables for long-term retention and analysis, or replay them to evaluate and improve agent performance over time. - -== AI Gateway - -The AI Gateway manages LLM provider access with two priorities: keeping your application up and keeping costs under control. - -For high availability, the gateway provides provider-agnostic routing with intelligent failover. Your users don't care which provider serves a request. They care that the application stays up. For fiscal control, you get per-tenant budgets and rate limiting, so there are no runaway costs and no surprise bills. - -The gateway also supports tenancy modeling for teams, individuals, applications, and service accounts, giving you chargeback transparency for internal cost allocation. You can proxy both models and MCP gateways, centralizing compliance for all LLM interactions without locking into any single provider. - -== Enterprise governance - -Redpanda ADP addresses critical enterprise requirements across all components. - -*Security by design*:: MCP servers enforce policies at the tool level, programmatically preventing prompt injection, SQL injection, and other agent-based attacks. Policy enforcement is deterministic and controlled. Agents cannot bypass security constraints even through creative prompting. - -*Unified authorization*:: All components use OIDC-based authentication with an on-behalf-of authorization model. When a user invokes an agent, the agent inherits the intersection of its own permissions and the user's permissions. This ensures proper data access scoping. - -*Complete observability*:: Redpanda ADP provides two levels of inspection. Execution logs (transcripts) capture every agent action with 100% sampling using OpenTelemetry standards. Real-time debugging tools allow you to inspect individual MCP server calls down to individual tool invocations with full timing data. You can view detailed agent actions in glossterm:Redpanda Console[] and replay data for agent evaluations. - -*Compliance and audit*:: For industries requiring multi-year audit trails, Redpanda ADP records every agent action and data source used in decision-making. Execution logs are stored in Redpanda topics and can be materialized to Iceberg tables for long-term retention and analysis. - -== Use cases - -Organizations use Redpanda ADP to: - -* *Automate operational workflows*: Create specialized agents for building management, infrastructure monitoring, compliance reporting, and other domain-specific tasks. -* *Monitor manufacturing and operations*: Deploy multi-agent systems that analyze factory machine telemetry in real-time, detect anomalies, search equipment manuals, and create maintenance tickets automatically. -* *Extend enterprise productivity tools*: Integrate Microsoft Copilot or other workplace agents with internal data sources and systems that are otherwise inaccessible. - -== Next steps - -* xref:ai-agents:mcp/overview.adoc[] -* xref:ai-agents:mcp/remote/quickstart.adoc[] -* xref:ai-agents:mcp/local/quickstart.adoc[] From f1daf734f86ff4ad9cfa8f400849af0c5dd1a034 Mon Sep 17 00:00:00 2001 From: micheleRP Date: Mon, 9 Feb 2026 12:08:28 -0700 Subject: [PATCH 11/11] fix index.adoc --- modules/ai-agents/pages/index.adoc | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) diff --git a/modules/ai-agents/pages/index.adoc b/modules/ai-agents/pages/index.adoc index d4af999fc..73ea4dc12 100644 --- a/modules/ai-agents/pages/index.adoc +++ b/modules/ai-agents/pages/index.adoc @@ -1,10 +1,4 @@ -= AI Agents in Redpanda Cloud -:description: Learn about AI agents and the tools Redpanda Cloud provides for building them. += Redpanda Agentic Data Plane +:description: Redpanda Agentic Data Plane (ADP) provides enterprise-grade infrastructure for building, deploying, and governing AI agents at scale with enterprise governance, cost controls, and compliance-grade audit trails. :page-layout: index :page-aliases: develop:agents/about.adoc, develop:ai-agents/about.adoc - -glossterm:AI agent[,AI agents] are configurable assistants that autonomously perform specialist tasks by leveraging large language models (LLMs) and connecting to external data sources and tools. - -Redpanda's xref:ai-agents:adp-overview.adoc[Agentic Data Plane (ADP)] provides enterprise-grade infrastructure for building, deploying, and governing AI agents at scale with four key components that deliver enterprise governance, cost controls, and compliance-grade audit trails. - -Redpanda Cloud provides two complementary Model Context Protocol (MCP) options to help you build AI agents.