# Redpanda

Redpanda is a Kafka® compatible, ZooKeeper®-free, JVM-free and source available streaming data platform. Use all your favorite open source tooling without any code changes.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Who's accountable when AI agents get it wrong?

DevFeed: [Who's accountable when AI agents get it wrong?](<https://devfeed.tech/articles/who-s-accountable-when-ai-agents-get-it-wrong-138117.md>)

Original publisher: [Read original article](<https://www.redpanda.com/blog/ai-agent-accountability-observability>)

Author: Kristin Crosier

Published: 2026-11-16T00:00:00Z

Content type: article

Language: en

Sources: [Redpanda](<https://devfeed.tech/sources/redpanda.md>)

Topics: [ai-governance](<https://devfeed.tech/topics/ai-governance.md>), [agent observability](<https://devfeed.tech/topics/agent-observability.md>), [observability](<https://devfeed.tech/topics/observability.md>), [Access Control](<https://devfeed.tech/topics/access-control.md>)

Tags: [accountability](<https://devfeed.tech/tags/accountability.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-systems](<https://devfeed.tech/tags/agentic-systems.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-accountability](<https://devfeed.tech/tags/ai-accountability.md>), [ai-act](<https://devfeed.tech/tags/ai-act.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agent-accountability](<https://devfeed.tech/tags/ai-agent-accountability.md>), [ai-agent-governance](<https://devfeed.tech/tags/ai-agent-governance.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-governance](<https://devfeed.tech/tags/ai-governance.md>), [ai-observability](<https://devfeed.tech/tags/ai-observability.md>), [ai-projects](<https://devfeed.tech/tags/ai-projects.md>), [ai-systems](<https://devfeed.tech/tags/ai-systems.md>), [governance](<https://devfeed.tech/tags/governance.md>), [it](<https://devfeed.tech/tags/it.md>), [observability](<https://devfeed.tech/tags/observability.md>), [risk](<https://devfeed.tech/tags/risk.md>), [thought-leadership](<https://devfeed.tech/tags/thought-leadership.md>)

### AI overview

The excerpt argues that agent accountability depends on observability and ownership planned early, because complex systems of agents, tools, and permissions become harder to monitor and govern after deployment. It recommends assessing what agents do and which systems they touch, mapping risks and naming accountable owners early, then grounding later controls such as alerts, evaluations, and kill switches in that visibility. The article cites Gartner's projection that over half of failed AI projects by 2028 will stem from weak accountability rather than model performance. It says annual reviews and inventory spreadsheets are insufficient as systems grow, but the excerpt does not include the promised detailed use cases or full episode guidance. Redpanda's Agentic Data Plane is presented as a governed gateway with identity, auditing, scope limits, and kill switches.

### Source excerpt

When an AI agent gets it wrong, who's accountable? Learn why accountability starts with observability and how to mitigate risk with AI governance.

## Introducing R2: Redpanda's new engine

DevFeed: [Introducing R2: Redpanda's new engine](<https://devfeed.tech/articles/introducing-r2-redpanda-s-new-engine-130609.md>)

Original publisher: [Read original article](<https://www.redpanda.com/blog/r2-the-engine-of-engines>)

Author: Alexander Gallego

Published: 2026-11-12T00:00:00Z

Content type: release

Language: en

Sources: [Redpanda](<https://devfeed.tech/sources/redpanda.md>)

Topics: [Redpanda](<https://devfeed.tech/topics/redpanda-data-streaming.md>), [Test automation](<https://devfeed.tech/topics/test-automation.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>)

Tags: [accelerators](<https://devfeed.tech/tags/accelerators.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-coding](<https://devfeed.tech/tags/agentic-coding.md>), [ai](<https://devfeed.tech/tags/ai.md>), [announcement](<https://devfeed.tech/tags/announcement.md>), [async](<https://devfeed.tech/tags/async.md>), [bandwidth](<https://devfeed.tech/tags/bandwidth.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [c-plus-plus-23](<https://devfeed.tech/tags/c-plus-plus-23.md>), [clickbench](<https://devfeed.tech/tags/clickbench.md>), [clock](<https://devfeed.tech/tags/clock.md>), [clocks](<https://devfeed.tech/tags/clocks.md>), [cluster](<https://devfeed.tech/tags/cluster.md>), [engine](<https://devfeed.tech/tags/engine.md>), [faster](<https://devfeed.tech/tags/faster.md>), [foundation](<https://devfeed.tech/tags/foundation.md>), [future](<https://devfeed.tech/tags/future.md>), [products](<https://devfeed.tech/tags/products.md>), [r2](<https://devfeed.tech/tags/r2.md>), [sql](<https://devfeed.tech/tags/sql.md>), [streaming](<https://devfeed.tech/tags/streaming.md>)

### AI overview

R2 is Redpanda's new shared engine for Streaming, SQL, and future products, starting with version 26.3.1. It uses C++23 coroutines and a one-reactor-per-core runtime, with `io_uring` on Linux, `kqueue` on macOS, and a simulated I/O source for deterministic, replayable tests. The article describes formal TLA+ and Lean checks alongside simulation, and `mimalloc` for memory allocation; Redpanda says this approach has exposed bugs before production. In tests of Redpanda SQL on S3, the R2 port used 35 threads per node versus 20,000-23,000 for the threaded version at 64 clients. Cold scans improved most, while warm ClickBench was roughly level (1.02x excluding one regex query) and peak memory use was 20-30% higher. From 26.3.1, Streaming/Operator will no longer be source available; Community Edition remains free up to 50 cores.

### Source excerpt

R2 is Redpanda's new engine, the shared foundation for Redpanda Streaming, SQL and future products, built to be faster to develop and harder to break.

## Multi-team access control for Redpanda Agentic Data Plane

DevFeed: [Multi-team access control for Redpanda Agentic Data Plane](<https://devfeed.tech/articles/multi-team-access-control-for-redpanda-agentic-data-plane-129182.md>)

Original publisher: [Read original article](<https://www.redpanda.com/blog/multi-team-governance-agentic-data-plane>)

Author: Mustafa El-Hilo

Published: 2026-11-09T00:00:00Z

Content type: article

Language: en

Sources: [Redpanda](<https://devfeed.tech/sources/redpanda.md>)

Topics: [Access Control](<https://devfeed.tech/topics/access-control.md>), [Dynamic authorization rules](<https://devfeed.tech/topics/dynamic-authorization-rules.md>), [Authorization](<https://devfeed.tech/topics/authorization.md>), [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [control-plane](<https://devfeed.tech/topics/control-plane.md>), [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>)

Tags: [access-control](<https://devfeed.tech/tags/access-control.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [policies](<https://devfeed.tech/tags/policies.md>), [tags](<https://devfeed.tech/tags/tags.md>), [team](<https://devfeed.tech/tags/team.md>), [tutorial](<https://devfeed.tech/tags/tutorial.md>)

### AI overview

Redpanda Agentic Data Plane uses tag-based ABAC policies written in Cedar to let teams self-serve within a shared deployment. The example assigns each resource one `team` tag matching an IdP group; additional tags mark shared providers (`shared=true`) and agent lifecycle (`stage=dev` or `prod`). Builder teams get policies for their agents, MCP servers, and tool calls, while a platform group manages policies and cross-team access. Shared providers and production agents can be used by everyone under separate permits; a forbid keeps dev agents callable only by their creator, and other forbids block untagged agents and reserve team-tag changes for platform operators. Releasing an agent is a stage-tag change, so adding resources or releasing agents does not require new policies; new teams or personas do. The excerpt says the model needs twelve policies for its example, and notes that group names must match IdP spelling exactly and users in multiple groups receive each group's permits.

### Source excerpt

How Redpanda Agentic Data Plane uses tags and Cedar policies so every team can build, release, and share agents on one platform, with the decisions you need to make first.

## How we built an AI IT assistant for an enterprise service desk

DevFeed: [How we built an AI IT assistant for an enterprise service desk](<https://devfeed.tech/articles/how-we-built-an-ai-it-assistant-for-an-enterprise-service-desk-102792.md>)

Original publisher: [Read original article](<https://www.redpanda.com/blog/build-ai-agent-it-service-desk-requests>)

Author: Michael Golfi

Published: 2026-10-27T00:00:00Z

Content type: article

Language: en

Sources: [Redpanda](<https://devfeed.tech/sources/redpanda.md>)

Topics: [Support](<https://devfeed.tech/topics/support.md>), [request management](<https://devfeed.tech/topics/request-management.md>), [API Governance](<https://devfeed.tech/topics/api-governance.md>), [Microsoft Teams](<https://devfeed.tech/topics/microsoft-teams.md>), [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [Redpanda](<https://devfeed.tech/topics/redpanda-data-streaming.md>)

Tags: [account](<https://devfeed.tech/tags/account.md>), [actor](<https://devfeed.tech/tags/actor.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-instructions](<https://devfeed.tech/tags/agent-instructions.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agent-governance](<https://devfeed.tech/tags/ai-agent-governance.md>), [ai-assistant](<https://devfeed.tech/tags/ai-assistant.md>), [control](<https://devfeed.tech/tags/control.md>), [data](<https://devfeed.tech/tags/data.md>), [desk](<https://devfeed.tech/tags/desk.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [it](<https://devfeed.tech/tags/it.md>), [microsoft](<https://devfeed.tech/tags/microsoft.md>), [microsoft-teams](<https://devfeed.tech/tags/microsoft-teams.md>), [service](<https://devfeed.tech/tags/service.md>), [service-desk](<https://devfeed.tech/tags/service-desk.md>), [teams](<https://devfeed.tech/tags/teams.md>)

### AI overview

The assistant handles IT requests in Microsoft Teams, answers some questions from existing knowledge articles, and gathers required details before submitting incidents or catalog requests through the customer's existing ITSM workflows. It reads form definitions at request time, so supported form changes do not need a separate release; the ITSM platform retains its records, permissions, and approval workflows. In its first week, it answered 36% of employee requests on its own, without creating tickets or involving people. Each employee's own account governs changes, while a separately scoped read-only account supplies form definitions and lookups. A task-specific MCP server exposes defined IT actions, and the Redpanda Agentic Data Plane gateway controls access and can enforce data policies and guardrails. The excerpt notes that some controls depend on configuration and version, data policies are in preview, and it does not establish which optional controls were enabled for this customer. Audit and trace records help operators investigate outcomes but can contain sensitive data.

### Source excerpt

See how an AI agent on the Redpanda Agentic Data Plane answers and routes service desk requests in Microsoft Teams, while IT stays in control.

## Build an AI agent once and reuse it across teams

DevFeed: [Build an AI agent once and reuse it across teams](<https://devfeed.tech/articles/build-an-ai-agent-once-and-reuse-it-across-teams-95864.md>)

Original publisher: [Read original article](<https://www.redpanda.com/blog/how-to-build-and-reuse-ai-agents>)

Author: Daniel Takabayashi

Published: 2026-10-22T00:00:00Z

Content type: article

Language: en

Sources: [Redpanda](<https://devfeed.tech/sources/redpanda.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [agent observability](<https://devfeed.tech/topics/agent-observability.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [Microsoft Teams](<https://devfeed.tech/topics/microsoft-teams.md>)

Tags: [a2a](<https://devfeed.tech/tags/a2a.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent2agent](<https://devfeed.tech/tags/agent2agent.md>), [agent2agent-protocol](<https://devfeed.tech/tags/agent2agent-protocol.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-gateway](<https://devfeed.tech/tags/ai-gateway.md>), [alert](<https://devfeed.tech/tags/alert.md>), [audit](<https://devfeed.tech/tags/audit.md>), [build](<https://devfeed.tech/tags/build.md>), [governance](<https://devfeed.tech/tags/governance.md>), [hr](<https://devfeed.tech/tags/hr.md>), [identity](<https://devfeed.tech/tags/identity.md>), [it](<https://devfeed.tech/tags/it.md>), [observability](<https://devfeed.tech/tags/observability.md>), [ops](<https://devfeed.tech/tags/ops.md>), [reuse](<https://devfeed.tech/tags/reuse.md>), [teams](<https://devfeed.tech/tags/teams.md>), [tutorial](<https://devfeed.tech/tags/tutorial.md>)

### AI overview

Redpanda's Agentic Data Plane is presented as a way to build an internal capability agent once and let other teams or event-driven pipelines call it under shared governance. A managed IT Assist agent connects to ServiceNow through Redpanda-hosted MCP tools, keeps credentials in a secret store, authorizes actions as the requesting employee, and applies tool access policies outside the model. A self-managed onboarding orchestrator can discover and call it over A2A while adding Workday and SharePoint agents through an OpenAPI-generated MCP server or a fronted existing MCP server. For operations, Redpanda Connect can send alerts to a triage agent, which composes existing agents and uses a pipeline service identity with narrowly granted permissions. The excerpt also describes per-agent budgets, GitOps management, transcript retention choices, and centralized traces and run records for reviewing delegated work and avoiding unsafe duplicate catalog submissions. It gives a product-specific architecture example; it does not establish comparative results against other platforms.

### Source excerpt

Learn how to build an AI agent once and reuse it across IT, HR, and ops teams, with shared governance, identity, and observability.

## Why agentic AI pilots stall before production | Redpanda

DevFeed: [Why agentic AI pilots stall before production | Redpanda](<https://devfeed.tech/articles/why-agentic-ai-pilots-stall-before-production-redpanda-92900.md>)

Original publisher: [Read original article](<https://www.redpanda.com/blog/why-agentic-ai-pilots-fail>)

Author: Kristin Crosier

Published: 2026-10-20T00:00:00Z

Content type: article

Language: en

Sources: [Redpanda](<https://devfeed.tech/sources/redpanda.md>)

Topics: [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [Production Engineering](<https://devfeed.tech/topics/production-engineering.md>)

Tags: [adoption](<https://devfeed.tech/tags/adoption.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agentic-systems](<https://devfeed.tech/tags/agentic-systems.md>), [agents](<https://devfeed.tech/tags/agents.md>), [agents-in-production](<https://devfeed.tech/tags/agents-in-production.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-kill-switch](<https://devfeed.tech/tags/ai-kill-switch.md>), [ai-projects](<https://devfeed.tech/tags/ai-projects.md>), [ai-startup](<https://devfeed.tech/tags/ai-startup.md>), [api](<https://devfeed.tech/tags/api.md>), [apps](<https://devfeed.tech/tags/apps.md>), [auditing](<https://devfeed.tech/tags/auditing.md>), [building-trust](<https://devfeed.tech/tags/building-trust.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [data](<https://devfeed.tech/tags/data.md>), [production](<https://devfeed.tech/tags/production.md>), [projects](<https://devfeed.tech/tags/projects.md>), [workforce](<https://devfeed.tech/tags/workforce.md>)

### AI overview

The excerpt identifies data readiness and workforce adoption as key reasons agentic AI pilots stall before production. It says teams need to assess their data before building agentic systems and give employees a structured process for learning to work with AI; adoption may take a year or more, with projects often stalling around trust and habit formation. Production agents face messy data, infrastructure glitches, governance demands, and the ability to affect live systems, unlike demos. When a pilot fails in real conditions, the source suggests narrowing its scope. Teams should also weigh the engineering cost of building and managing infrastructure in-house against buying it. The excerpt promotes Redpanda's Agentic Data Plane as a governed gateway with identity, auditing, scope limits, and kill switches.

### Source excerpt

Learn about the top reasons agentic AI projects stall before reaching production, and how to get your data and your workforce AI-ready.

## 4 digital transformation use cases in manufacturing with Redpanda

DevFeed: [4 digital transformation use cases in manufacturing with Redpanda](<https://devfeed.tech/articles/4-digital-transformation-use-cases-in-manufacturing-with-redpanda-66858.md>)

Original publisher: [Read original article](<https://www.redpanda.com/blog/digital-transformation-manufacturing-use-cases>)

Author: Peter Corless

Published: 2026-10-06T00:00:00Z

Content type: article

Language: en

Sources: [Redpanda](<https://devfeed.tech/sources/redpanda.md>)

Topics: [Redpanda](<https://devfeed.tech/topics/redpanda-data-streaming.md>), [Event-Streaming](<https://devfeed.tech/topics/event-streaming.md>), [Redpanda BYOC](<https://devfeed.tech/topics/redpanda-byoc.md>), [Confluent Platform](<https://devfeed.tech/topics/confluent-platform.md>), [Confluent Cloud](<https://devfeed.tech/topics/confluent-cloud.md>), [shadow AI](<https://devfeed.tech/topics/shadow-ai.md>), [AI for data automation](<https://devfeed.tech/topics/ai-for-data-automation.md>)

Tags: [agentic-ai-governance](<https://devfeed.tech/tags/agentic-ai-governance.md>), [apache-kafka](<https://devfeed.tech/tags/apache-kafka.md>), [azure](<https://devfeed.tech/tags/azure.md>), [byoc-deployment](<https://devfeed.tech/tags/byoc-deployment.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [cost](<https://devfeed.tech/tags/cost.md>), [customer](<https://devfeed.tech/tags/customer.md>), [data-driven](<https://devfeed.tech/tags/data-driven.md>), [data-platform](<https://devfeed.tech/tags/data-platform.md>), [digital-transformation](<https://devfeed.tech/tags/digital-transformation.md>), [manufacturing](<https://devfeed.tech/tags/manufacturing.md>), [powers](<https://devfeed.tech/tags/powers.md>), [real-time-data-streaming](<https://devfeed.tech/tags/real-time-data-streaming.md>)

### AI overview

The article presents four manufacturing case studies using Redpanda for real-time data streaming and AI-related operations. GlobalFoundries is building a shared data foundation across global operations and using AI to support change management. Range Energy adopted Redpanda's managed BYOC service, Rivian replaced a Kafka deployment after encountering a scaling and reliability concern, and Johnson Controls reports annual cost savings after migrating its streaming platform.

### Source excerpt

See how Redpanda powers real-time data streaming and agentic AI governance for global manufacturers.

## Why a model-level kill switch does not control an AI agent's access and actions

DevFeed: [Why a model-level kill switch does not control an AI agent's access and actions](<https://devfeed.tech/articles/your-ai-kill-switch-is-in-the-wrong-place-61251.md>)

Original publisher: [Read original article](<https://www.redpanda.com/blog/ai-killswitch-in-model-is-not-agentic-governance>)

Author: Marc Millstone

Published: 2026-09-28T00:00:00Z

Content type: article

Language: en

Sources: [Redpanda](<https://devfeed.tech/sources/redpanda.md>)

Topics: [ai security](<https://devfeed.tech/topics/ai-security.md>), [AI for customer service automation](<https://devfeed.tech/topics/ai-for-customer-service-automation.md>), [LLM security](<https://devfeed.tech/topics/llm-security.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-kill-switch](<https://devfeed.tech/tags/ai-kill-switch.md>), [api-keys](<https://devfeed.tech/tags/api-keys.md>), [thought-leadership](<https://devfeed.tech/tags/thought-leadership.md>)

### AI overview

The article argues that model-level safety controls do not define what an AI agent can access or do in business systems. Sandboxes, network allowlists, and scoped API keys limit reach, but may not distinguish an appropriate action from a harmful one, such as deleting a test environment versus production. It calls for boundaries enforced around agents with business context.

### Source excerpt

A kill switch on the model doesn't protect your systems. See why enterprises need to own the boundary agents operate inside, not just the model behind them.

## 8 engineering lessons on running AI agents in production

DevFeed: [8 engineering lessons on running AI agents in production](<https://devfeed.tech/articles/8-engineering-lessons-on-running-ai-agents-in-production-58396.md>)

Original publisher: [Read original article](<https://www.redpanda.com/blog/run-ai-agents-scale-engineering-operations>)

Author: Redpanda

Published: 2026-09-22T00:00:00Z

Content type: article

Language: en

Sources: [Redpanda](<https://devfeed.tech/sources/redpanda.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [big-data](<https://devfeed.tech/topics/big-data.md>), [data-processing](<https://devfeed.tech/topics/data-processing.md>), [Security](<https://devfeed.tech/topics/security.md>), [Software](<https://devfeed.tech/topics/software.md>), [systems](<https://devfeed.tech/topics/systems.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [big-data](<https://devfeed.tech/tags/big-data.md>), [control](<https://devfeed.tech/tags/control.md>), [data](<https://devfeed.tech/tags/data.md>), [data-processing](<https://devfeed.tech/tags/data-processing.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [governance](<https://devfeed.tech/tags/governance.md>), [production](<https://devfeed.tech/tags/production.md>), [security](<https://devfeed.tech/tags/security.md>), [system](<https://devfeed.tech/tags/system.md>)

### AI overview

An article distills lessons from building a security platform that processed petabytes of data daily before adding AI agents. It focuses on production concerns such as governance, data access, permissions, operational processes, and deciding which workflow steps should remain human-controlled.

### Source excerpt

Red Canary processed petabytes of security data a day before layering agents on top. Brian Beyer and Joe Moles on what that takes in production.

## Streamhouse Working Group proposes a vendor-neutral architecture for real-time data infrastructure

DevFeed: [Streamhouse Working Group proposes a vendor-neutral architecture for real-time data infrastructure](<https://devfeed.tech/articles/why-streamhouse-mission-critical-data-and-ai-need-infrastructure-built-for-live-26772.md>)

Original publisher: [Read original article](<https://www.redpanda.com/blog/streamhouse-working-group-ai-infrastructure>)

Author: Alexander Gallego

Published: 2026-09-15T00:00:00Z

Content type: opinion

Language: en

Sources: [Redpanda](<https://devfeed.tech/sources/redpanda.md>)

Topics: [Data Infrastructure](<https://devfeed.tech/topics/data-infrastructure.md>), [real-time](<https://devfeed.tech/topics/real-time.md>), [Streaming](<https://devfeed.tech/topics/streaming.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Redpanda-Connect](<https://devfeed.tech/topics/redpanda-connect.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [announcement](<https://devfeed.tech/tags/announcement.md>), [data-infrastructure](<https://devfeed.tech/tags/data-infrastructure.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [redpanda-connect](<https://devfeed.tech/tags/redpanda-connect.md>), [streaming](<https://devfeed.tech/tags/streaming.md>)

### AI overview

Redpanda says it has joined Aiven, Confluent, StreamNative, and Ververica to form the Streamhouse Working Group, which proposes a vendor-neutral architecture for real-time operational data infrastructure. The article distinguishes Streamhouse from the lakehouse by focusing on continuously processing current data for production applications and AI agents.

### Source excerpt

Redpanda has joined Aiven, Confluent, StreamNative, and Ververica to form the Streamhouse Working Group. Here's what that means for the future of real-time data infrastructure.

## Redpanda named a Leader in G2's Fall 2026 Event Stream Processing Reports

DevFeed: [Redpanda named a Leader in G2's Fall 2026 Event Stream Processing Reports](<https://devfeed.tech/articles/redpanda-named-a-leader-in-g2-s-fall-2026-event-stream-processing-reports-12700.md>)

Original publisher: [Read original article](<https://www.redpanda.com/blog/g2-fall-2026-results>)

Author: Redpanda

Published: 2026-09-01T00:00:00Z

Content type: article

Language: en

Sources: [Redpanda](<https://devfeed.tech/sources/redpanda.md>)

Topics: [stream-processing](<https://devfeed.tech/topics/stream-processing.md>), [Usability](<https://devfeed.tech/topics/usability.md>), [real-time](<https://devfeed.tech/topics/real-time.md>), [Streaming](<https://devfeed.tech/topics/streaming.md>), [Software](<https://devfeed.tech/topics/software.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [announcement](<https://devfeed.tech/tags/announcement.md>), [event](<https://devfeed.tech/tags/event.md>), [performance](<https://devfeed.tech/tags/performance.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [reports](<https://devfeed.tech/tags/reports.md>), [software](<https://devfeed.tech/tags/software.md>), [stream-processing](<https://devfeed.tech/tags/stream-processing.md>), [streaming](<https://devfeed.tech/tags/streaming.md>), [usability](<https://devfeed.tech/tags/usability.md>)

### AI overview

Redpanda reports that it was recognized in 10 G2 Fall 2026 Event Stream Processing reports, earning first place in eight indexes, including implementation, usability, results, and relationship. The article also highlights Redpanda Shadowing for migration from Confluent and cites a 4.7 out of 5 average rating across 53 G2 reviews.

### Source excerpt

Redpanda ranked #1 in Implementation, Usability, Results, and Relationship Indexes in G2's Fall 2026 Event Stream Processing Reports.

## CoreBreak proves agent guardrails need to live outside the agent

DevFeed: [CoreBreak proves agent guardrails need to live outside the agent](<https://devfeed.tech/articles/corebreak-proves-agent-guardrails-need-to-live-outside-the-agent-12689.md>)

Original publisher: [Read original article](<https://www.redpanda.com/blog/corebreak-ai-agent-vulnerability>)

Author: Tyler Akidau

Published: 2026-08-31T00:00:00Z

Content type: opinion

Language: en

Sources: [Redpanda](<https://devfeed.tech/sources/redpanda.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Security](<https://devfeed.tech/topics/security.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>), [Amazon Web Services](<https://devfeed.tech/topics/aws.md>), [vercel ai sdk](<https://devfeed.tech/topics/vercel-ai-sdk.md>), [Amazon Bedrock](<https://devfeed.tech/topics/amazon-bedrock.md>), [Google](<https://devfeed.tech/topics/google.md>), [Vercel](<https://devfeed.tech/topics/vercel.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [aws](<https://devfeed.tech/tags/aws.md>), [bedrock](<https://devfeed.tech/tags/bedrock.md>), [cve](<https://devfeed.tech/tags/cve.md>), [google](<https://devfeed.tech/tags/google.md>), [policy](<https://devfeed.tech/tags/policy.md>), [security](<https://devfeed.tech/tags/security.md>), [thought-leadership](<https://devfeed.tech/tags/thought-leadership.md>), [vercel](<https://devfeed.tech/tags/vercel.md>)

### AI overview

The article argues that CoreBreak exposed a structural security flaw in major AI agent stacks and that agent guardrails should be enforced outside the agent's control.

### Source excerpt

At Black Hat 2026, CoreBreak exposed the same structural flaw across AWS, Google, and Vercel. Here's why AI agent security enforcement should live beyond the agent's reach.

## Push-button migration from Confluent to Redpanda with Shadowing

DevFeed: [Push-button migration from Confluent to Redpanda with Shadowing](<https://devfeed.tech/articles/push-button-migration-from-confluent-to-redpanda-with-shadowing-12715.md>)

Original publisher: [Read original article](<https://www.redpanda.com/blog/migrate-confluent-redpanda-shadowing>)

Author: Trevor Blackford

Published: 2026-08-25T00:00:00Z

Content type: article

Language: en

Sources: [Redpanda](<https://devfeed.tech/sources/redpanda.md>)

Topics: [migration](<https://devfeed.tech/topics/migration.md>), [Replication](<https://devfeed.tech/topics/replication.md>), [Apache Kafka](<https://devfeed.tech/topics/apache-kafka.md>), [Confluent Cloud](<https://devfeed.tech/topics/confluent-cloud.md>), [Confluent Platform](<https://devfeed.tech/topics/confluent-platform.md>), [Disaster Recovery](<https://devfeed.tech/topics/disaster-recovery.md>), [Usability](<https://devfeed.tech/topics/usability.md>)

Tags: [big-bang](<https://devfeed.tech/tags/big-bang.md>), [confluent-cloud](<https://devfeed.tech/tags/confluent-cloud.md>), [confluent-platform](<https://devfeed.tech/tags/confluent-platform.md>), [data-centers](<https://devfeed.tech/tags/data-centers.md>), [disaster-recovery](<https://devfeed.tech/tags/disaster-recovery.md>), [kafka](<https://devfeed.tech/tags/kafka.md>), [migration](<https://devfeed.tech/tags/migration.md>), [replication](<https://devfeed.tech/tags/replication.md>), [schema](<https://devfeed.tech/tags/schema.md>)

### AI overview

The article presents Redpanda Shadowing 26.2 as a low-risk migration path from Confluent Cloud, Confluent Platform, or other Apache Kafka-compatible clusters. It replicates topic data, schemas, offsets, and ACLs while preserving offsets, allowing teams to validate workloads and move applications individually instead of using a big-bang cutover.

### Source excerpt

Migrate off Confluent without the "big cutover weekend." Redpanda Shadowing carries topic data, schemas, offsets, and ACLs on a single link. Available on Self-Managed , BYOC, and Dedicated.

## 4 FAQs about designing agentic systems for production

DevFeed: [4 FAQs about designing agentic systems for production](<https://devfeed.tech/articles/4-faqs-about-designing-agentic-systems-for-production-12694.md>)

Original publisher: [Read original article](<https://www.redpanda.com/blog/designing-agentic-systems-architect-faqs>)

Author: Kristin Crosier

Published: 2026-08-19T00:00:00Z

Content type: article

Language: en

Sources: [Redpanda](<https://devfeed.tech/sources/redpanda.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [ai-governance](<https://devfeed.tech/topics/ai-governance.md>), [Responsibility & Safety](<https://devfeed.tech/topics/responsibility-safety.md>), [software-architecture](<https://devfeed.tech/topics/software-architecture.md>), [observability](<https://devfeed.tech/topics/observability.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-governance](<https://devfeed.tech/tags/ai-governance.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [cheat-sheet](<https://devfeed.tech/tags/cheat-sheet.md>), [observability](<https://devfeed.tech/tags/observability.md>), [security](<https://devfeed.tech/tags/security.md>)

### AI overview

This article presents practical guidance for designing and operating enterprise AI agents in production. It focuses on governance, policy enforcement, data access controls, observability, immutable action logs, audit transcripts, emergency shutdown capabilities, and guardrails for token and budget usage.

### Source excerpt

Learn about the technical challenges many organizations face while deploying agentic systems, and how to ensure AI agents can operate safely and consistently.

## Multi-region high availability for Kafka workloads with a single Stretch Cluster

DevFeed: [Multi-region high availability for Kafka workloads with a single Stretch Cluster](<https://devfeed.tech/articles/multi-region-high-availability-for-kafka-workloads-with-a-single-stretch-cluster-12718.md>)

Original publisher: [Read original article](<https://www.redpanda.com/blog/multi-region-high-availability-kafka-stretch-clusters>)

Author: David Yu

Published: 2026-08-11T00:00:00Z

Content type: article

Language: en

Sources: [Redpanda](<https://devfeed.tech/sources/redpanda.md>)

Topics: [Apache Kafka](<https://devfeed.tech/topics/apache-kafka.md>), [Kubernetes](<https://devfeed.tech/topics/kubernetes.md>), [Availability](<https://devfeed.tech/topics/availability.md>), [Replication](<https://devfeed.tech/topics/replication.md>), [Raft](<https://devfeed.tech/topics/raft.md>), [Resilience](<https://devfeed.tech/topics/resilience.md>), [stream-processing](<https://devfeed.tech/topics/stream-processing.md>)

Tags: [clusters](<https://devfeed.tech/tags/clusters.md>), [k8s](<https://devfeed.tech/tags/k8s.md>), [kafka](<https://devfeed.tech/tags/kafka.md>), [raft](<https://devfeed.tech/tags/raft.md>), [release](<https://devfeed.tech/tags/release.md>), [replication](<https://devfeed.tech/tags/replication.md>), [resilience](<https://devfeed.tech/tags/resilience.md>), [stream-processing](<https://devfeed.tech/tags/stream-processing.md>)

### AI overview

Redpanda Operator 26.2 introduces generally available Stretch Clusters, allowing one logical Redpanda cluster to span multiple Kubernetes clusters and regions. The release provides synchronous replication with Raft-based automatic failover, safer broker rolling restarts, Redpanda Connect pipelines as Kubernetes resources, and Gateway API support for Redpanda Console.

### Source excerpt

Redpanda Operator 26.2 brings GA Stretch Clusters for multi-region replication, Redpanda Connect pipelines as K8s resources, Gateway API support, and safer rolling restarts.

## Out-of-band Policy Engine: governance AI agents can't ignore

DevFeed: [Out-of-band Policy Engine: governance AI agents can't ignore](<https://devfeed.tech/articles/out-of-band-policy-engine-governance-ai-agents-can-t-ignore-12668.md>)

Original publisher: [Read original article](<https://www.redpanda.com/blog/agentic-ai-needs-out-of-band-governance>)

Author: Tyler Akidau

Published: 2026-08-03T00:00:00Z

Content type: opinion

Language: en

Sources: [Redpanda](<https://devfeed.tech/sources/redpanda.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [shadow AI](<https://devfeed.tech/topics/shadow-ai.md>), [Security](<https://devfeed.tech/topics/security.md>), [audit trail](<https://devfeed.tech/topics/audit-trail.md>), [Language models](<https://devfeed.tech/topics/language-models.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [announcement](<https://devfeed.tech/tags/announcement.md>), [audit-trail](<https://devfeed.tech/tags/audit-trail.md>), [governance](<https://devfeed.tech/tags/governance.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [mcp-server](<https://devfeed.tech/tags/mcp-server.md>), [policy](<https://devfeed.tech/tags/policy.md>), [security](<https://devfeed.tech/tags/security.md>), [shadow-ai](<https://devfeed.tech/tags/shadow-ai.md>)

### AI overview

The article argues that enterprises need out-of-band governance for AI agents because agents can create shadow AI and may alter safeguards or audit trails that they can access. It presents Redpanda's Out-of-Band Policy Engine and Agentic Data Plane as an approach in which policies remain outside the agent's reach.

### Source excerpt

Somewhere in your company, right now, someone is building an agent. Here's how the latest release of Redpanda's Agentic Data Plane makes it safe to run them.

## Agentic kill switch is a database problem. So we built Redpanda SQL

DevFeed: [Agentic kill switch is a database problem. So we built Redpanda SQL](<https://devfeed.tech/articles/agentic-kill-switch-is-a-database-problem-so-we-built-redpanda-sql-12728.md>)

Original publisher: [Read original article](<https://www.redpanda.com/blog/query-real-time-analytics-google-cloud>)

Author: Alexander Gallego

Published: 2026-08-03T00:00:00Z

Content type: article

Language: en

Sources: [Redpanda](<https://devfeed.tech/sources/redpanda.md>)

Topics: [Database](<https://devfeed.tech/topics/database.md>), [SQL](<https://devfeed.tech/topics/sql.md>), [stream-processing](<https://devfeed.tech/topics/stream-processing.md>), [Google Cloud Platform (GCP)](<https://devfeed.tech/topics/google-cloud.md>), [Amazon Web Services](<https://devfeed.tech/topics/aws.md>), [systems](<https://devfeed.tech/topics/systems.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [announcement](<https://devfeed.tech/tags/announcement.md>), [aws](<https://devfeed.tech/tags/aws.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [code](<https://devfeed.tech/tags/code.md>), [database](<https://devfeed.tech/tags/database.md>), [exploit](<https://devfeed.tech/tags/exploit.md>), [google-cloud](<https://devfeed.tech/tags/google-cloud.md>), [governance](<https://devfeed.tech/tags/governance.md>), [models](<https://devfeed.tech/tags/models.md>), [olap](<https://devfeed.tech/tags/olap.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [scale](<https://devfeed.tech/tags/scale.md>), [sql](<https://devfeed.tech/tags/sql.md>), [stream-processing](<https://devfeed.tech/tags/stream-processing.md>), [systems](<https://devfeed.tech/tags/systems.md>), [tools](<https://devfeed.tech/tags/tools.md>)

### AI overview

The article presents Redpanda SQL as a database built for agentic governance. It describes real-time bridge queries, efficient SQL JOINs, a ring-buffer shuffle algorithm, and analytical processing designed to detect agent behavior and provide an agentic kill switch. Redpanda SQL is stated to be available on AWS and Google Cloud.

### Source excerpt

Agentic governance needs a new kind of database, so we built Redpanda SQL. Now available on both AWS and Google Cloud.

## 10X more data, same 4 seconds: single-query scaling in Redpanda SQL on 1TB

DevFeed: [10X more data, same 4 seconds: single-query scaling in Redpanda SQL on 1TB](<https://devfeed.tech/articles/10x-more-data-same-4-seconds-single-query-scaling-in-redpanda-sql-on-1tb-12771.md>)

Original publisher: [Read original article](<https://www.redpanda.com/blog/single-query-scaling-redpanda-sql>)

Author: Marcin Grzebieluch

Published: 2026-07-29T00:00:00Z

Content type: article

Language: en

Sources: [Redpanda](<https://devfeed.tech/sources/redpanda.md>)

Topics: [SQL](<https://devfeed.tech/topics/sql.md>), [Benchmark](<https://devfeed.tech/topics/benchmark.md>), [dataset](<https://devfeed.tech/topics/dataset.md>), [Apache Iceberg](<https://devfeed.tech/topics/apache-iceberg.md>), [Streaming](<https://devfeed.tech/topics/streaming.md>)

Tags: [apache](<https://devfeed.tech/tags/apache.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [kafka](<https://devfeed.tech/tags/kafka.md>), [sql](<https://devfeed.tech/tags/sql.md>), [streaming](<https://devfeed.tech/tags/streaming.md>)

### AI overview

This article benchmarks how a single analytical query in Redpanda SQL scales as the dataset grows from 100 GB to 1 TB and as cluster resources increase. Redpanda SQL combines live-streaming topics with historical Apache Iceberg tables through bridge queries, and the benchmark uses skewed NYC Taxi trip data to evaluate strong scaling and query feasibility.

### Source excerpt

A benchmark on how a single analytical query behaves in Redpanda SQL as the dataset and the cluster grow.

## Drag, drop, done: a visual composer for Redpanda Connect

DevFeed: [Drag, drop, done: a visual composer for Redpanda Connect](<https://devfeed.tech/articles/drag-drop-done-a-visual-composer-for-redpanda-connect-12749.md>)

Original publisher: [Read original article](<https://www.redpanda.com/blog/redpanda-connect-pipeline-builder>)

Author: Prakhar Garg

Published: 2026-07-23T00:00:00Z

Content type: article

Language: en

Sources: [Redpanda](<https://devfeed.tech/sources/redpanda.md>)

Topics: [Redpanda-Connect](<https://devfeed.tech/topics/redpanda-connect.md>), [Canvas](<https://devfeed.tech/topics/canvas.md>), [stream-processing](<https://devfeed.tech/topics/stream-processing.md>), [Cache](<https://devfeed.tech/topics/cache.md>), [Routing (disambiguation)](<https://devfeed.tech/topics/routing.md>), [HTTP](<https://devfeed.tech/topics/http.md>), [n8n](<https://devfeed.tech/topics/n8n.md>), [workflow automation](<https://devfeed.tech/topics/workflow-automation.md>)

Tags: [api](<https://devfeed.tech/tags/api.md>), [automation](<https://devfeed.tech/tags/automation.md>), [building](<https://devfeed.tech/tags/building.md>), [cache](<https://devfeed.tech/tags/cache.md>), [caching](<https://devfeed.tech/tags/caching.md>), [events](<https://devfeed.tech/tags/events.md>), [front-end](<https://devfeed.tech/tags/front-end.md>), [http](<https://devfeed.tech/tags/http.md>), [n8n](<https://devfeed.tech/tags/n8n.md>), [pipeline](<https://devfeed.tech/tags/pipeline.md>), [redpanda-connect](<https://devfeed.tech/tags/redpanda-connect.md>), [routing](<https://devfeed.tech/tags/routing.md>), [stream-processing](<https://devfeed.tech/tags/stream-processing.md>), [workflow](<https://devfeed.tech/tags/workflow.md>)

### AI overview

Redpanda introduces a visual Pipeline Builder for Redpanda Connect, using a drag-and-drop canvas to compose pipelines from inputs, processors, and outputs. The builder generates YAML while making routing, enrichment, caching, error handling, and retries easier to understand and configure. The article contrasts it with n8n, emphasizing Redpanda Connect's suitability for high-volume event streaming with ordering, backpressure, and exactly-once semantics.

### Source excerpt

A first look at the new visual Pipeline Builder for Redpanda Connect (preview), plus a roundup of recent CDC and connector updates.

## Deploy agents you can trust with centralized AI governance

DevFeed: [Deploy agents you can trust with centralized AI governance](<https://devfeed.tech/articles/deploy-agents-you-can-trust-with-centralized-ai-governance-12693.md>)

Original publisher: [Read original article](<https://www.redpanda.com/blog/deploy-agents-you-can-trust-with-centralized-ai-governance>)

Author: Kristin Crosier

Published: 2026-07-21T00:00:00Z

Content type: article

Language: en

Sources: [Redpanda](<https://devfeed.tech/sources/redpanda.md>)

Topics: [ai-governance](<https://devfeed.tech/topics/ai-governance.md>), [Responsibility & Safety](<https://devfeed.tech/topics/responsibility-safety.md>), [audit trail](<https://devfeed.tech/topics/audit-trail.md>), [observability](<https://devfeed.tech/topics/observability.md>), [Security Information and Event Management (SIEM)](<https://devfeed.tech/topics/siem-security.md>), [Model Context Protocol](<https://devfeed.tech/topics/model-context-protocol.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-governance](<https://devfeed.tech/tags/ai-governance.md>), [audit-trail](<https://devfeed.tech/tags/audit-trail.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [autonomous-agents](<https://devfeed.tech/tags/autonomous-agents.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [hosting](<https://devfeed.tech/tags/hosting.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [observability](<https://devfeed.tech/tags/observability.md>), [thought-leadership](<https://devfeed.tech/tags/thought-leadership.md>), [vibe-coding](<https://devfeed.tech/tags/vibe-coding.md>)

### AI overview

This article explains why enterprises struggle to deploy autonomous agentic systems: organizations lack confidence in agents that can access data and tools without unique identities, audit trails, or kill switches. It argues for a centralized AI governance layer enforced by infrastructure that agents cannot access or modify, positioned between agents and the data, tools, identities, and models they use. The proposed governance platform also supports scaling through AI gateways, MCP hosting, observability, and budgeting.

### Source excerpt

Discover why organizations are struggling to deploy and scale agentic systems, and how a centralized AI governance platform can help you trust and scale agents.

## Full CDC semantics land in the Iceberg output for Redpanda Connect

DevFeed: [Full CDC semantics land in the Iceberg output for Redpanda Connect](<https://devfeed.tech/articles/full-cdc-semantics-land-in-the-iceberg-output-for-redpanda-connect-12681.md>)

Original publisher: [Read original article](<https://www.redpanda.com/blog/cdc-semantics-iceberg-redpanda-connect>)

Author: Prakhar Garg

Published: 2026-07-14T00:00:00Z

Content type: article

Language: en

Sources: [Redpanda](<https://devfeed.tech/sources/redpanda.md>)

Topics: [Apache Iceberg](<https://devfeed.tech/topics/apache-iceberg.md>), [clickhouse](<https://devfeed.tech/topics/clickhouse.md>), [Database](<https://devfeed.tech/topics/database.md>), [Apache Kafka](<https://devfeed.tech/topics/apache-kafka.md>)

Tags: [analytics](<https://devfeed.tech/tags/analytics.md>), [clickhouse](<https://devfeed.tech/tags/clickhouse.md>), [data](<https://devfeed.tech/tags/data.md>), [database](<https://devfeed.tech/tags/database.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [product](<https://devfeed.tech/tags/product.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [redpanda-connect](<https://devfeed.tech/tags/redpanda-connect.md>), [streams](<https://devfeed.tech/tags/streams.md>), [sync](<https://devfeed.tech/tags/sync.md>)

### AI overview

This hands-on article explains how Redpanda Connect v4.99.0 applies full change data capture semantics to Apache Iceberg tables. Its output supports row-level inserts, upserts, and deletes, allowing a lakehouse table to stay synchronized with a source database in real time through a single pipeline definition.

### Source excerpt

Full CDC semantics in Iceberg mean the lakehouse reflects what the source database looks like right now, not what it looked like during last night's batch window. Get to know the latest addition to Redpanda Connect.

## What is an Agentic Data Plane?

DevFeed: [What is an Agentic Data Plane?](<https://devfeed.tech/articles/what-is-an-agentic-data-plane-12781.md>)

Original publisher: [Read original article](<https://www.redpanda.com/blog/what-is-an-agentic-data-plane>)

Author: Marc Millstone

Published: 2026-07-09T00:00:00Z

Content type: article

Language: en

Sources: [Redpanda](<https://devfeed.tech/sources/redpanda.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [agent observability](<https://devfeed.tech/topics/agent-observability.md>), [Amazon API Gateway](<https://devfeed.tech/topics/amazon-api-gateway.md>), [AWS IAM](<https://devfeed.tech/topics/aws-iam.md>), [observability](<https://devfeed.tech/topics/observability.md>), [Security Information and Event Management (SIEM)](<https://devfeed.tech/topics/siem-security.md>), [Amazon Web Services](<https://devfeed.tech/topics/aws.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [api](<https://devfeed.tech/tags/api.md>), [api-gateway](<https://devfeed.tech/tags/api-gateway.md>), [aws](<https://devfeed.tech/tags/aws.md>), [bedrock](<https://devfeed.tech/tags/bedrock.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [governance](<https://devfeed.tech/tags/governance.md>), [iam](<https://devfeed.tech/tags/iam.md>), [identity](<https://devfeed.tech/tags/identity.md>), [identity-management](<https://devfeed.tech/tags/identity-management.md>), [llm](<https://devfeed.tech/tags/llm.md>), [models](<https://devfeed.tech/tags/models.md>), [observability](<https://devfeed.tech/tags/observability.md>), [siem](<https://devfeed.tech/tags/siem.md>), [thought-leadership](<https://devfeed.tech/tags/thought-leadership.md>), [token](<https://devfeed.tech/tags/token.md>), [tool](<https://devfeed.tech/tags/tool.md>), [tools](<https://devfeed.tech/tags/tools.md>)

### AI overview

The article defines an Agentic Data Plane as a governed governance and runtime layer between enterprise AI agents and the data, tools, identities, and models they access. It explains why existing IAM, API gateways, and observability or SIEM systems do not adequately govern agent-specific actions, identity propagation, model selection, token spending, policy enforcement, and end-to-end tracing.

### Source excerpt

The Agentic Data Plane is the governance and runtime layer that connects your AI agents to everything they act on. Learn what it does, why existing tools can't replace it, and what to look for in an enterprise-grade one.

## Stream Oracle changes to ClickHouse in real time

DevFeed: [Stream Oracle changes to ClickHouse in real time](<https://devfeed.tech/articles/stream-oracle-changes-to-clickhouse-in-real-time-12774.md>)

Original publisher: [Read original article](<https://www.redpanda.com/blog/stream-oracle-changes-to-clickhouse-real-time-cdc>)

Author: Prakhar Garg

Published: 2026-07-07T00:00:00Z

Content type: tutorial

Language: en

Sources: [Redpanda](<https://devfeed.tech/sources/redpanda.md>)

Topics: [clickhouse](<https://devfeed.tech/topics/clickhouse.md>), [Redpanda-Connect](<https://devfeed.tech/topics/redpanda-connect.md>), [Oracle Database](<https://devfeed.tech/topics/oracle-database.md>), [Apache Kafka](<https://devfeed.tech/topics/apache-kafka.md>), [real-time](<https://devfeed.tech/topics/real-time.md>), [data](<https://devfeed.tech/topics/data.md>), [Database](<https://devfeed.tech/topics/database.md>), [YAML](<https://devfeed.tech/topics/yaml.md>)

Tags: [clickhouse](<https://devfeed.tech/tags/clickhouse.md>), [connectors](<https://devfeed.tech/tags/connectors.md>), [data](<https://devfeed.tech/tags/data.md>), [database](<https://devfeed.tech/tags/database.md>), [event](<https://devfeed.tech/tags/event.md>), [integration](<https://devfeed.tech/tags/integration.md>), [kafka](<https://devfeed.tech/tags/kafka.md>), [oracle](<https://devfeed.tech/tags/oracle.md>), [pipeline](<https://devfeed.tech/tags/pipeline.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [redpanda-connect](<https://devfeed.tech/tags/redpanda-connect.md>), [schema](<https://devfeed.tech/tags/schema.md>), [yaml](<https://devfeed.tech/tags/yaml.md>)

### AI overview

A hands-on walkthrough shows how to stream Oracle change data capture events through Redpanda Connect into ClickHouse in real time. It uses Oracle LogMiner and YAML-configured pipelines, with a Redpanda topic serving as an intermediate store before data is delivered to ClickHouse or other destinations.

### Source excerpt

A hands-on walkthrough of the new Oracle input in Redpanda Connect. No Debezium, no Kafka Connect runtime, no JVM.

## Real-time Change Data Capture with Redpanda Connect and MySQL

DevFeed: [Real-time Change Data Capture with Redpanda Connect and MySQL](<https://devfeed.tech/articles/real-time-change-data-capture-with-redpanda-connect-and-mysql-12735.md>)

Original publisher: [Read original article](<https://www.redpanda.com/blog/real-time-cdc-my-sql>)

Author: Chandler Mayo

Published: 2026-07-02T00:00:00Z

Content type: tutorial

Language: en

Sources: [Redpanda](<https://devfeed.tech/sources/redpanda.md>)

Topics: [MySQL](<https://devfeed.tech/topics/mysql.md>), [Apache Kafka](<https://devfeed.tech/topics/apache-kafka.md>), [Database](<https://devfeed.tech/topics/database.md>), [Docker Compose](<https://devfeed.tech/topics/docker-compose.md>), [real-time](<https://devfeed.tech/topics/real-time.md>), [Docker](<https://devfeed.tech/topics/docker.md>), [SQL](<https://devfeed.tech/topics/sql.md>)

Tags: [apache-kafka](<https://devfeed.tech/tags/apache-kafka.md>), [connectors](<https://devfeed.tech/tags/connectors.md>), [container](<https://devfeed.tech/tags/container.md>), [docker](<https://devfeed.tech/tags/docker.md>), [event](<https://devfeed.tech/tags/event.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [kafka](<https://devfeed.tech/tags/kafka.md>), [mysql](<https://devfeed.tech/tags/mysql.md>), [network](<https://devfeed.tech/tags/network.md>), [pipeline](<https://devfeed.tech/tags/pipeline.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [sql](<https://devfeed.tech/tags/sql.md>), [tutorial](<https://devfeed.tech/tags/tutorial.md>), [volume](<https://devfeed.tech/tags/volume.md>)

### AI overview

A step-by-step tutorial for building a real-time change data capture pipeline with MySQL and Redpanda Connect. It explains how row-level inserts, updates, and deletes become downstream events without polling, using compatibility with the Kafka Connect ecosystem.

### Source excerpt

A step-by-step tutorial on how to stream every insert, update, and delete from your database using MySQL and a faster, simpler alternative to Kafka Connect.

[Next page](<https://devfeed.tech/sources/redpanda.md?cursor=WyIyMDI2LTA3LTAyVDAwOjAwOjAwKzAwOjAwIiwgImVmZWRhNzg2LTFhZjktNGMyMS1iZmE4LWIwODY1OWFjM2E3NCJd>)