# AI Architecture Published articles for AI Architecture. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Kubernetes Multi-Cluster Project Karmada Reaches CNCF Graduation DevFeed: [Kubernetes Multi-Cluster Project Karmada Reaches CNCF Graduation]() Original publisher: [Read original article]() Author: Claudio Masolo Published: 2026-09-17T10:00:00Z Content type: news Language: en Sources: [InfoQ]() Topics: [Kubernetes](), [Orchestration](), [Cloud](), [Computing]() Tags: [ai-architecture](), [cloud](), [cluster](), [clusters](), [cncf](), [devops](), [karmada-kubernetes-cncf](), [kubernetes](), [multi-cloud](), [news](), [orchestration](), [project](), [release]() ### AI overview The CNCF announced that Karmada, a multi-cluster and multi-cloud Kubernetes orchestration project, graduated to its highest maturity tier. The announcement coincided with Karmada v1.19, which improves multi-component scheduling for AI training jobs and makes priority-based scheduling available by default in Beta. ### Source excerpt The Cloud Native Computing Foundation (CNCF) announced on September 2026 that Karmada, a multi-cluster and multi-cloud Kubernetes orchestration project, has graduated. This multi-cluster and multi-cloud Kubernetes orchestration project reached CNCF's highest maturity tier. By Claudio Masolo ## Dropbox Outlines How Focusing on Existing Infrastructure Efficiency Can Create Headroom for AI DevFeed: [Dropbox Outlines How Focusing on Existing Infrastructure Efficiency Can Create Headroom for AI]() Original publisher: [Read original article]() Author: Matt Foster Published: 2026-09-16T07:15:00Z Content type: news Language: en Sources: [InfoQ]() Topics: [Artificial Intelligence](), [cloud-infrastructure](), [Magic Pocket](), [data centers](), [networking]() Tags: [ai](), [ai-architecture](), [ai-ml-data-engineering](), [capacity](), [cloud](), [data-center](), [data-storage](), [devops](), [dropbox](), [dropbox-datacenter](), [efficiency](), [infrastructure](), [infrastructure-optimisation](), [magic-pocket](), [ml-data-engineering](), [networking](), [news](), [optimization](), [storage](), [sustainable-computing]() ### AI overview Dropbox describes how long-running infrastructure optimization helps it accommodate growing AI demand by improving forecasting, fleet utilization, storage density, hardware lifecycles, and rack-level power delivery. Its storage infrastructure has used more than 50% less power per petabyte since 2020. ### Source excerpt Dropbox has outlined how a decade of infrastructure optimization is helping it absorb growing demand from AI without treating new data-center capacity as the only answer. Its work spans forecasting, fleet utilization, storage density, hardware lifecycles, and rack-level power delivery, much of it predating the current AI boom. By Matt Foster ## Presentation: Decision Models in Agentic Architectures: From Production to Agent Skills DevFeed: [Presentation: Decision Models in Agentic Architectures: From Production to Agent Skills]() Original publisher: [Read original article]() Author: Alex Porcelli Published: 2026-09-14T11:00:00Z Content type: article Language: en Sources: [InfoQ]() Topics: [Agent Skills](), [Artificial Intelligence](), [Large Language Model](), [NeMo]() Tags: [agent](), [agent-skills](), [agentic](), [agentic-ai-architecture](), [agents](), [ai](), [ai-architecture](), [ai-ml-data-engineering](), [architecture](), [architecture-design](), [architectures](), [artificial-intelligence](), [business](), [decision-models-agentic-ai](), [development](), [enterprise](), [enterprise-architecture](), [governance](), [infoq](), [large-language-models](), [llms](), [ml-data-engineering](), [models](), [nemo](), [presentation](), [production](), [qcon-ai-boston-2026](), [qcon-software-development-conference](), [skills](), [transcripts]() ### AI overview Alex Porcelli explains how DMN decision models can be integrated with LLMs, agent skills, and NeMo guardrails to create auditable and deterministic agentic architectures for high-stakes enterprise decisions. ### Source excerpt Alex Porcelli discusses the critical gap in enterprise AI: non-deterministic output and lack of accountability in high-stakes decisions. He shares how integrating DMN decision models with LLMs, agent skills, and NeMo guardrails creates auditable, deterministic agentic architectures - allowing business leaders to own decision logic while engineers maintain robust architectural governance. By Alex Porcelli ## Podcast: How Will We Train Developers If AI Does the Routine Work: A Conversation with Scott Hanselman DevFeed: [Podcast: How Will We Train Developers If AI Does the Routine Work: A Conversation with Scott Hanselman]() Original publisher: [Read original article]() Author: Scott Hanselman Published: 2026-09-14T11:00:00Z Content type: article Language: en Sources: [InfoQ]() Topics: [Artificial Intelligence](), [AI Development](), [Architecture & Design](), [coding]() Tags: [agentic-ai](), [agents](), [ai](), [ai-agents](), [ai-architecture](), [ai-ml-data-engineering](), [architecture](), [architecture-design](), [artificial-intelligence](), [code](), [developers](), [infoq](), [junior-developers](), [ml-data-engineering](), [podcast](), [software-engineering](), [the-infoq-podcast](), [train-developers-ai-routine-work]() ### AI overview The podcast discusses how to train software engineers when AI agents perform much of the routine work traditionally assigned to junior developers. Scott Hanselman advocates a preceptorship model, experienced engineers overseeing AI-generated work, and long-term investment in mentorship and human connection. ### Source excerpt In this podcast, Michael Stiefel spoke to Scott Hanselman about developing new software engineers when artificial intelligence agents are doing most of the work on which junior developers were trained. Hanselman suggests the software industry should adopt a preceptorship model similar to the nursing profession. By Scott Hanselman ## Presentation: From Retrieval to Reasoning: Building Production-Ready Agentic AI Systems with Knowledge Graphs DevFeed: [Presentation: From Retrieval to Reasoning: Building Production-Ready Agentic AI Systems with Knowledge Graphs]() Original publisher: [Read original article]() Author: Cassie Shum Published: 2026-09-12T11:00:00Z Content type: tutorial Language: en Sources: [InfoQ]() Topics: [Graphs](), [Architecture & Design](), [Retrieval Augmented Generation (RAG)](), [Code]() Tags: [agentic-ai](), [agentic-ai-architecture](), [agents](), [ai](), [ai-architecture](), [ai-ml-data-engineering](), [architecture](), [architecture-design](), [artificial-intelligence](), [code](), [development](), [engineering](), [infoq](), [knowledge-graph](), [knowledge-graphs-agentic-systems-patterns](), [large-language-models](), [ml-data-engineering](), [presentation](), [production](), [qcon-ai-boston-2026](), [qcon-software-development-conference](), [rag](), [reasoning](), [retrieval-augmented-generation](), [transcripts]() ### AI overview A presentation on using knowledge graphs as a foundation for production-ready agentic AI systems. It covers architectural patterns for context bundling, decision provenance, code as truth, and agent visibility, along with a graph-based engineering harness for feedback loops, token optimization, and reliability. ### Source excerpt Cassie Shum discusses why knowledge graphs serve as a critical foundation for agentic systems. Moving beyond basic RAG, she explains 4 practical architectural patterns: context bundling, decision provenance, code as truth, and agent visibility. She demonstrates an engineering harness built on a knowledge graph to streamline feedback loops, optimize token usage, and maintain system reliability. By Cassie Shum ## Introducing IBM and NASA's new foundation model for the Moon DevFeed: [Introducing IBM and NASA's new foundation model for the Moon]() Original publisher: [Read original article]() Author: Kim Martineau Published: 2026-09-10T12:30:00Z Content type: article Language: en Sources: [IBM Research]() Topics: [lunar foundation model](), [ibm](), [foundation-models](), [data](), [Artificial Intelligence](), [AI Architecture]() Tags: [accelerated-discovery](), [ai](), [ai-architecture](), [algorithms](), [ibm](), [lunar-foundation-model](), [mapping](), [model](), [nasa](), [release](), [science](), [space](), [us]() ### AI overview IBM and NASA are open-sourcing the NASA-IBM Lunar Foundation Model, a multimodal AI model that integrates lunar observations from US and Japanese missions across viewing angles, spatial scales, and measurement types. The model is intended to support lunar mapping, volcanic-history research, and searches for polar ice. ### Source excerpt The multi-modal model could help astronauts navigate craters, investigate ancient lava, and search for ice, as the US plans for a long-term lunar presence. ## A Unified Data Architecture For Sovereign Agentic AI With VMware Tanzu And VMware vSAN DevFeed: [A Unified Data Architecture For Sovereign Agentic AI With VMware Tanzu And VMware vSAN]() Original publisher: [Read original article]() Author: arnab chakraborty Published: 2026-09-03T23:27:50Z Content type: article Language: en Sources: [VMware Blogs]() Topics: [Agentic AI Architecture](), [AI Architecture](), [data-architecture](), [AI Agent](), [cloud-infrastructure](), [Latency](), [real-time](), [Security](), [data-processing]() Tags: [agentic-ai](), [agentic-ai-architecture](), [ai](), [ai-architecture](), [blog](), [cloud](), [data-architecture](), [efficiency](), [infrastructure](), [latency](), [modern-apps](), [real-time](), [security]() ### AI overview The article presents a unified, on-premises data architecture for sovereign agentic AI using VMware Tanzu, VMware Tanzu Greenplum, VMware Cloud Foundation, and VMware vSAN. It argues that placing AI compute close to enterprise data can improve performance and cost while reducing latency, data-transfer fees, and compliance risks. ### Source excerpt By combining VMware Tanzu Greenplum with VMware vSAN, organizations can bring their AI compute directly to their data storage layer for improved cost and latency. The post A Unified Data Architecture For Sovereign Agentic AI With VMware Tanzu And VMware vSAN appeared first on Tanzu. The post A Unified Data Architecture For Sovereign Agentic AI With VMware Tanzu And VMware vSAN appeared first on VMware Blogs. ## The Thundering Herd Problem in Agentic AI: Why Traditional Fixes Fall Short DevFeed: [The Thundering Herd Problem in Agentic AI: Why Traditional Fixes Fall Short]() Original publisher: [Read original article]() Author: Quentin Packard Published: 2026-06-19T00:00:00Z Content type: article Language: en Sources: [Cockroach Labs]() Topics: [Agentic AI Architecture](), [agent orchestration](), [AI Agent](), [Artificial Intelligence](), [Concurrency]() Tags: [agent-orchestration](), [agentic-ai](), [ai-architecture](), [load-testing](), [parallel](), [thundering-herd]() ### AI overview This article examines how agentic AI can create a thundering herd through intentional fan-out and parallel execution. It argues that traditional mitigations only partly transfer because agent-generated synchronization can produce a sharp saturation point that staging load tests may not reveal. ### Source excerpt The thundering herd of the past was externally triggered. ## Agentic AI Architecture: How CockroachDB Supports Memory, Context, and Control DevFeed: [Agentic AI Architecture: How CockroachDB Supports Memory, Context, and Control]() Original publisher: [Read original article]() Author: Alejandro Infanzon Published: 2026-06-11T00:00:00Z Content type: article Language: en Sources: [Cockroach Labs]() Topics: [Agentic AI Architecture](), [CockroachDB](), [Artificial Intelligence](), [AI Architecture](), [context](), [Databases](), [data](), [Resilience](), [audit](), [SQL](), [Back end](), [Cockroach Labs]() Tags: [agentic](), [agentic-ai](), [agentic-ai-architecture](), [agents](), [ai](), [ai-agents](), [ai-architecture](), [architecture](), [audit](), [backend](), [cockroachdb](), [context](), [data](), [database](), [databases](), [durability](), [infrastructure](), [latency](), [low-latency](), [memory]() ### AI overview This article explains how CockroachDB can support enterprise agentic AI architectures by storing durable agent state, long-term memory, retrieval metadata, schema context, permissions, execution metadata, cost information, latency telemetry, and SQL audit trails. It presents the database as an operational layer for observing, governing, and improving autonomous agent behavior. ### Source excerpt What happens when you connect a fleet of autonomous AI agents to your enterprise data stack? You quickly discover... ## AI Agents Need Context to Reason, Not Just Data DevFeed: [AI Agents Need Context to Reason, Not Just Data]() Original publisher: [Read original article]() Author: Quentin Packard Published: 2026-05-28T00:00:00Z Content type: article Language: en Sources: [Cockroach Labs]() Topics: [Artificial Intelligence](), [context](), [AI Agent](), [Agentic AI Architecture](), [Data Infrastructure]() Tags: [agentic-ai](), [agents](), [ai](), [ai-architecture](), [context](), [data-infrastructure](), [database]() ### AI overview The article argues that production failures in AI agents often stem from inadequate context management rather than the model itself. Reliable agent behavior requires current data, memory, permissions, observability, and awareness of system constraints, making context management a data infrastructure problem beyond basic retrieval or prompt engineering. ### Source excerpt When your AI agent makes a bad decision in production, what do you blame? ## Five principles for governed autonomy with enterprise AI DevFeed: [Five principles for governed autonomy with enterprise AI]() Original publisher: [Read original article]() Author: Robert Siwicki Published: 2026-04-28T00:00:00Z Content type: article Language: en Sources: [Redpanda]() Topics: [Artificial Intelligence](), [AI Agent](), [observability](), [AI Architecture](), [Streaming](), [real-time](), [Resilience](), [data](), [systems]() Tags: [agentic](), [ai](), [ai-agent](), [ai-architecture](), [architecture](), [customer](), [enterprise](), [event](), [governance](), [logs](), [memory](), [observability](), [real-time](), [resilience](), [streaming](), [thought-leadership](), [tool](), [workflows]() ### AI overview The article presents five principles for evolving Redleader, Redpanda's customer Slackbot, into a governed multi-agent architecture. It emphasizes stable streams, event-based coordination, human oversight, explicit terminal states, and real-time observability to make agent behavior reliable, replayable, measurable, and scalable. ### Source excerpt How to turn opaque agent behavior into governed, provable workflows. Based on our own tried and true experience with Redpanda's customer Slackbot. ## LLaDA: A Diffusion-Based Language Model for Revisable Text Generation DevFeed: [LLaDA: A Diffusion-Based Language Model for Revisable Text Generation]() Original publisher: [Read original article]() Published: 2025-02-17T00:00:00Z Content type: article Language: en Sources: [Tim Kellogg]() Topics: [diffusion-transformers](), [Large Language Model](), [AI Architecture]() Tags: [ai-architecture](), [consistency](), [diffusion](), [hallucinations](), [language](), [llms](), [model]() ### AI overview The article introduces LLaDA, a language model that uses diffusion rather than autoregressive next-token prediction. It explains how this approach can generate and revise text globally, potentially helping with hallucinations, reasoning loops, and coherence in structured writing such as contracts. ### Source excerpt A new language model uses diffusion instead of next-token prediction. That means the text it can back out of a hallucination before it commits. This is a big win for areas like law & contracts, where global consistency is valued