Skip to content

Commit 3a3671d

Browse files
Paulo BorgesPaulo Borges
authored andcommitted
Merge branch 'update-cloud-overview-adp-focus' into adp-pkg1
# Conflicts: # modules/ai-agents/pages/index.adoc # modules/get-started/pages/cloud-overview.adoc
2 parents 5c7310b + ac0ec9d commit 3a3671d

5 files changed

Lines changed: 91 additions & 31 deletions

File tree

modules/ROOT/nav.adoc

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -24,6 +24,7 @@
2424
** xref:get-started:cluster-types/create-dedicated-cloud-cluster.adoc[]
2525
2626
* xref:ai-agents:index.adoc[Agentic AI]
27+
** xref:ai-agents:adp-overview.adoc[ADP Overview]
2728
** xref:ai-agents:mcp/index.adoc[MCP]
2829
*** xref:ai-agents:mcp/overview.adoc[Overview]
2930
*** xref:ai-agents:mcp/remote/index.adoc[Remote MCP]
Lines changed: 74 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,74 @@
1+
= Redpanda Agentic Data Plane Overview
2+
:description: Enterprise-grade infrastructure for building, deploying, and governing AI agents at scale with compliance-grade audit trails.
3+
:page-topic-type: overview
4+
:page-categories: AI, Agentic AI
5+
:personas: evaluator, ai_agent_developer, platform_admin
6+
:learning-objective-1: Identify the key components of Redpanda ADP and their purposes
7+
:learning-objective-2: Describe how each component addresses enterprise governance and reliability requirements
8+
:learning-objective-3: Determine whether Redpanda ADP fits your organization's requirements for AI agent deployment
9+
10+
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.
11+
12+
After reading this page, you will be able to:
13+
14+
* [ ] {learning-objective-1}
15+
* [ ] {learning-objective-2}
16+
* [ ] {learning-objective-3}
17+
18+
NOTE: The Agentic Data Plane is supported on BYOC clusters running with AWS and Redpanda version 25.3 and later.
19+
20+
== AI Agents
21+
22+
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.
23+
24+
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.
25+
26+
The result is faster time-to-production, lower maintenance (declarative definitions instead of imperative code), and organizational consistency across teams.
27+
28+
== MCP Servers
29+
30+
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.
31+
32+
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.
33+
34+
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.
35+
36+
== Transcripts
37+
38+
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.
39+
40+
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.
41+
42+
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.
43+
44+
== AI Gateway
45+
46+
The AI Gateway manages LLM provider access with two priorities: keeping your application up and keeping costs under control.
47+
48+
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.
49+
50+
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.
51+
52+
== Enterprise governance
53+
54+
Redpanda ADP addresses critical enterprise requirements across all components.
55+
56+
*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.
57+
58+
*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.
59+
60+
*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.
61+
62+
*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.
63+
64+
== Use cases
65+
66+
Organizations use Redpanda ADP to:
67+
68+
* *Automate operational workflows*: Create specialized agents for building management, infrastructure monitoring, compliance reporting, and other domain-specific tasks.
69+
* *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.
70+
* *Extend enterprise productivity tools*: Integrate Microsoft Copilot or other workplace agents with internal data sources and systems that are otherwise inaccessible.
71+
72+
== Next steps
73+
74+
* xref:ai-agents:mcp/overview.adoc[]

modules/ai-agents/pages/index.adoc

Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -2,3 +2,9 @@
22
:description: Learn about the Redpanda Agentic Data Plane. Keep AI-powered apps highly available, control costs across providers, and govern access for teams, apps, and service accounts.
33
:page-layout: index
44
:page-aliases: develop:agents/about.adoc, develop:ai-agents/about.adoc
5+
6+
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.
7+
8+
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.
9+
10+
Redpanda Cloud provides two complementary Model Context Protocol (MCP) options to help you build AI agents.

modules/get-started/pages/cloud-overview.adoc

Lines changed: 8 additions & 23 deletions
Original file line numberDiff line numberDiff line change
@@ -6,33 +6,18 @@ Redpanda Cloud is a complete data streaming and agentic data plane platform deli
66

77
== Redpanda Agentic Data Plane (ADP)
88

9-
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.
9+
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.
1010

11-
NOTE: The Agentic Data Plane is supported on BYOC clusters running with AWS and Redpanda version 25.3 and later.
12-
13-
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:
14-
15-
* **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.
16-
* **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.
17-
* **AI Gateway**: Manage large language model (LLM) provider access with cost controls, rate limiting, intelligent routing, and failover support across multiple providers.
18-
//* **Catalog**: Maintain a centralized repository of agents, MCP servers, tools, and policies. Share components across teams and enforce organization-wide standards.
19-
20-
=== Enterprise capabilities for AI agents
21-
22-
Redpanda ADP addresses critical enterprise requirements for AI agent deployments:
11+
Redpanda ADP includes the following key components:
2312

24-
*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.
13+
* *AI Agents*: Declare the behavior you want instead of writing code. Redpanda powers declarative definitions with 300+ connectors.
14+
* *MCP Servers*: Translate agent intent into connections to your business systems using proven connectors, no glue code required.
15+
* *Transcripts*: End-to-end execution records built on an immutable log with formal correctness guarantees. Transcripts are the keystone of agent governance.
16+
* *AI Gateway*: High-availability model routing with fiscal controls and per-tenant cost attribution across LLM providers.
2517

26-
*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.
27-
28-
*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.
29-
30-
31-
* *Automate operational workflows*: Create specialized agents for building management, infrastructure monitoring, compliance reporting, and other domain-specific tasks
32-
* *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.
33-
* *Extend enterprise productivity tools*: Integrate Microsoft Copilot or other workplace agents with internal data sources and systems that are otherwise inaccessible
18+
NOTE: The Agentic Data Plane is supported on BYOC clusters running with AWS and Redpanda version 25.3 and later.
3419

35-
See also: xref:ai-agents:index.adoc[].
20+
To learn what makes Redpanda's approach unique, see xref:ai-agents:adp-overview.adoc[].
3621

3722
== Redpanda Cloud deployment options
3823

modules/get-started/pages/whats-new-cloud.adoc

Lines changed: 2 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -10,15 +10,9 @@ This page lists new features added to Redpanda Cloud.
1010

1111
=== Agentic Data Plane (ADP)
1212

13-
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.
13+
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+).
1414

15-
NOTE: The Agentic Data Plane is supported on BYOC clusters running with AWS and Redpanda version 25.3 and later.
16-
17-
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:
18-
19-
* **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.
20-
* **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.
21-
* **AI Gateway**: Manage large language model (LLM) provider access with cost controls, rate limiting, intelligent routing, and failover support across multiple providers.
15+
See xref:ai-agents:adp-overview.adoc[Agentic Data Plane Overview].
2216

2317
=== Serverless on AWS: GA
2418

0 commit comments

Comments
 (0)