You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: modules/ai-agents/pages/adp-overview.adoc
+20-7Lines changed: 20 additions & 7 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -7,31 +7,37 @@
7
7
:learning-objective-2: Describe how each component addresses enterprise governance and reliability requirements
8
8
:learning-objective-3: Determine whether Redpanda ADP fits your organization's requirements for AI agent deployment
9
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) combines a streaming-native immutable log, 300+ proven data connectors, and declarative AI agents into a unified platform with built-in compliance-grade audit trails.
10
+
As glossterm:AI agent[,AI agents] evolve from experimental prototypes to business-critical systems, companies face new challenges. How do you ensure your AI agents are reliable? How do you maintain control over costs and compliance? And how do you scale them across your organization without creating technical debt?
11
+
12
+
Redpanda Agentic Data Plane (ADP) solves these problems by bringing together key capabilities: a solid data foundation, over 300 proven connectors, and a declarative approach to building AI agents. The result is a unified platform that automatically tracks every agent decision for compliance and audit requirements.
11
13
12
14
After reading this page, you will be able to:
13
15
14
16
* [ ] {learning-objective-1}
15
17
* [ ] {learning-objective-2}
16
18
* [ ] {learning-objective-3}
17
19
18
-
NOTE: The Agentic Data Plane is supported on BYOC clusters running with AWS and Redpanda version 25.3 and later.
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.
24
+
With Redpanda AI agents, you declare the agent behavior you want and Redpanda handles execution and orchestration. Instead of writing Python or JavaScript, you define behaviors in YAML, orchestrate multiple specialized glossterm:subagent[,sub-agents], or bring your own frameworks like LangChain or LlamaIndex.
23
25
24
26
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
27
26
28
The result is faster time-to-production, lower maintenance (declarative definitions instead of imperative code), and organizational consistency across teams.
27
29
28
-
== MCP Servers
30
+
For more information, see xref:ai-agents:agents/overview.adoc[].
31
+
32
+
== MCP servers
29
33
30
34
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
35
32
36
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
37
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.
38
+
With 300+ out-of-the-box connectors and real-time debugging capabilities, you reduce integration time while getting enterprise-grade security. You can reuse your existing infrastructure and data sources rather than building new integrations from scratch.
39
+
40
+
For more information, see xref:ai-agents:mcp/overview.adoc[MCP Servers Overview].
35
41
36
42
== Transcripts
37
43
@@ -41,6 +47,8 @@ Transcripts are the keystone of agent governance. They are built on Redpanda's i
41
47
42
48
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
49
50
+
For more information, see xref:ai-agents:observability/concepts.adoc[Transcripts Overview].
51
+
44
52
== AI Gateway
45
53
46
54
The AI Gateway manages LLM provider access with two priorities: keeping your application up and keeping costs under control.
@@ -49,6 +57,8 @@ For high availability, the gateway provides provider-agnostic routing with intel
49
57
50
58
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
59
60
+
For more information, see xref:ai-agents:ai-gateway/what-is-ai-gateway.adoc[AI Gateway Overview].
61
+
52
62
== Enterprise governance
53
63
54
64
Redpanda ADP addresses critical enterprise requirements across all components.
@@ -71,4 +81,7 @@ Organizations use Redpanda ADP to:
Copy file name to clipboardExpand all lines: modules/ai-agents/pages/agents/index.adoc
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -2,4 +2,4 @@
2
2
:page-layout: index
3
3
:description: Declare agent behavior using built-in connectors in Redpanda Cloud. No custom agent code required.
4
4
5
-
Declare agent behavior by selecting an LLM and connecting tools from 300+ built-in Redpanda Connect connectors with filtering and data enrichment built in. No Python or JavaScript agent code required.
A transcript records the complete execution of an agentic behavior from start to finish. It captures every step — across multiple agents, tools, models, and services — in a single, traceable record. The AI Gateway and every glossterm:AI agent[,agent] and glossterm:MCP server[] in your Agentic Data Plane (ADP) automatically emit OpenTelemetry traces to a glossterm:topic[] called `redpanda.otel_traces`. Redpanda's immutable distributed log stores these traces.
Copy file name to clipboardExpand all lines: modules/ai-agents/pages/observability/view-transcripts.adoc
+2Lines changed: 2 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -22,6 +22,8 @@ For basic orientation on monitoring each Redpanda Agentic Data Plane component,
22
22
23
23
For conceptual background on what transcripts capture and how glossterm:span[spans] are organized hierarchically, see xref:ai-agents:observability/concepts.adoc[].
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].
5
+
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 data 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 glossterm:Redpanda Connect[].
6
6
7
7
== Redpanda Agentic Data Plane (ADP)
8
8
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.
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+ data connectors, and declarative agent definitions into a unified platform with built-in governance, cost controls, and compliance-grade audit trails.
10
10
11
11
Redpanda ADP includes the following key components:
12
12
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.
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
15
* *Transcripts*: End-to-end execution records built on an immutable log with formal correctness guarantees. Transcripts are the keystone of agent governance.
16
16
* *AI Gateway*: High-availability model routing with fiscal controls and per-tenant cost attribution across LLM providers.
17
17
18
-
NOTE: The Agentic Data Plane is supported on BYOC clusters running with AWS and Redpanda version 25.3 and later.
18
+
NOTE: Redpanda Agentic Data Plane is supported on BYOC clusters running with AWS and Redpanda version 25.3 and later.
19
19
20
-
To learn what makes Redpanda's approach unique, see xref:ai-agents:adp-overview.adoc[].
20
+
For more information, see xref:ai-agents:adp-overview.adoc[Redpanda Agentic Data Plane Overview].
21
21
22
22
== Redpanda Cloud deployment options
23
23
@@ -91,11 +91,6 @@ Redpanda Cloud applications are supported by three fully-managed deployment opti
91
91
| ✓
92
92
| ✓
93
93
94
-
| *Kafka Connect*
95
-
| ✗
96
-
| ✓ (disabled by default)
97
-
| ✓ (disabled by default)
98
-
99
94
| *RBAC & audit logs*
100
95
| ✗
101
96
| ✓
@@ -116,6 +111,11 @@ Redpanda Cloud applications are supported by three fully-managed deployment opti
xref:develop:managed-connectors/index.adoc[Kafka Connect] is disabled by default on all new clusters. To unlock this feature for your BYOC or Dedicated cluster, contact https://support.redpanda.com/hc/en-us/requests/new[Redpanda Support^]. When enabled, a Kafka Connect node runs even if no connectors are configured.
328
328
329
-
=== Redpanda Connect vs data transforms
330
-
331
-
xref:develop:data-transforms/how-transforms-work.adoc[Data transforms] (Wasm) provide lightweight, per-record changes between Redpanda topics with minimal latency. Transforms run inside the broker, map one input topic to one or more output topics, and are intentionally sandboxed (no external network or disk access). They're ideal for validation, redaction, format/schema conversion, and simple routing.
* Use Redpanda Connect if your pipeline must talk to external systems (HTTP services, databases, cloud storage), or when you need advanced flow control, such as batching and windowed processing.
366
362
====
367
363
364
+
=== Redpanda Connect vs data transforms
365
+
366
+
xref:develop:data-transforms/how-transforms-work.adoc[Data transforms] (Wasm) provide lightweight, per-record changes between Redpanda topics with minimal latency. Transforms run inside the broker, map one input topic to one or more output topics, and are intentionally sandboxed (no external network or disk access). They're ideal for validation, redaction, format/schema conversion, and simple routing.
367
+
368
368
== Redpanda Cloud vs Self-Managed feature compatibility
369
369
370
370
Because Redpanda Cloud is a fully-managed service that provides maintenance, data and partition balancing, upgrades, and recovery, much of the cluster maintenance required for Self-Managed users is not necessary for Redpanda Cloud users. Also, Redpanda Cloud is opinionated about Kafka configurations. For example, automatic topic creation is disabled. Some systems expect the Kafka service to automatically create topics when a message is produced to a topic that doesn't exist. (You can enable this for BYOC and Dedicated clusters with the `auto_create_topics_enabled` cluster property.)
@@ -400,12 +400,14 @@ Redpanda Cloud deployments do not support the following functionality available
400
400
+
401
401
NOTE: The `rpk cloud` commands are not supported in Self-Managed deployments.
402
402
403
+
403
404
== Features in limited availability
404
405
405
406
Features in limited availability are production-ready and are covered by Redpanda Support for early adopters.
406
407
407
408
The following features are currently in limited availability in Redpanda Cloud:
408
409
410
+
* xref:ai-agents:adp-overview.adoc[Redpanda ADP] including AI agents, AI Gateway, and transcripts
409
411
* Dedicated for Azure
410
412
411
413
== Features in beta
@@ -416,23 +418,15 @@ The following features are currently in beta in Redpanda Cloud:
416
418
417
419
* BYOVPC for AWS
418
420
* BYOVNet for Azure
419
-
* Secrets Management for BYOVPC on GCP and AWS
420
-
* xref:ai-agents:index.adoc[Redpanda ADP] including AI agents, MCP servers, AI Gateway, and Transcripts
421
+
* Secrets management for BYOVPC on GCP and AWS
421
422
* Several Redpanda Connect components
422
423
424
+
include::shared:partial$suggested-video.adoc[]
425
+
426
+
* https://www.youtube.com/watch?v=gVlzsJAYT64&ab_channel=RedpandaData[YouTube - What is Redpanda BYOC? (3 mins)^]
427
+
423
428
== Next steps
424
429
* xref:ai-agents:index.adoc[Build AI agents with Redpanda ADP]
425
430
* xref:manage:maintenance.adoc[Learn about upgrades and maintenance]
426
431
* xref:get-started:cluster-types/serverless.adoc[Create a Serverless cluster]
427
432
* xref:get-started:cluster-types/byoc/index.adoc[Create a BYOC cluster]
428
-
* xref:get-started:cluster-types/dedicated/create-dedicated-cloud-cluster-aws.adoc[Create a Dedicated cluster]
429
-
430
-
include::shared:partial$suggested-reading.adoc[]
431
-
432
-
* https://redpanda.com/blog/deploy-redpanda-clusters-cloud-aws-gcp[Bring Your Own Cloud (BYOC): best of both worlds^]
433
-
434
-
* https://redpanda.com/blog/data-sovereignty-fully-managed-cloud-byoc[A middle path for data sovereignty: Bring Your Own Cloud^]
435
-
436
-
include::shared:partial$suggested-video.adoc[]
437
-
438
-
* https://www.youtube.com/watch?v=gVlzsJAYT64&ab_channel=RedpandaData[YouTube - What is Redpanda BYOC? (3 mins)^]
0 commit comments