The New Stack Podcast

What began as an internal developer tool atBlockhas evolved into a broader open-source initiative with industry backing. Goose, Block’s AI coding agent, followed a path similar to Amazon’s transformation of internal infrastructure intoAmazon Web Services. After deploying Goose companywide, Block open-sourced the tool under a permissive license, leading to rapid adoption across the developer community.

But according to Manik Surtani, Office of the CTO, Block and Co Founder of Agentic AI Foundation, early momentum exposed governance challenges. Although Goose was technically open source, Block retained trademark ownership, creating concerns for enterprises seeking truly independent governance. To address this, the team partnered with the creators ofAnthropicand the Model Context Protocol community to establish theAgentic AI Foundationunder the umbrella of theLinux Foundation.

Goose, MCP, and Agents.MD became the foundation’s initial projects, chosen largely to accelerate the launch of the new organization and create a collaborative ecosystem around agentic AI development.

Learn more from The New Stack around the latest in open-source AI: 

Anthropic extends MCP with a UI framework

Why the Linux Foundation adopted MCP, with Jim Zemlin and Mazin Gilbert

Join our community of newsletter subscribers to stay on top of the news and at the top of your game. 

At Google Cloud Next 2026, Fivetran Chief Product Officer Anjan Kundavaram argued that enterprise data systems are unprepared for the scale of AI-driven analytics. Unlike humans, AI agents can generate exponentially more queries, often routing them through the same expensive compute infrastructure. Kundavaram compared it to “using a Lamborghini to mow the lawn.” To address this, Fivetran introduced its “Open Data Infrastructure” vision and a benchmark designed to expose hidden AI workload costs in closed ecosystems.

Kundavaram said agents can optimize for cost instead of speed, choosing cheaper compute engines when appropriate — but only in open architectures with multiple options. Closed systems force every query through high-cost paths. He also warned that fragmented data and weak context create a “triple whammy” of poor AI responses, soaring analytics bills, and wasted compute. While many organizations respond by tightening controls, Kundavaram argued the better path is investing in open infrastructure, interoperability, and strong semantic data practices before AI costs spiral further.

Learn more from The New Stack around the latest in enterprise data systems: 

Enterprise AI Success Demands Real-Time Data Platforms

AI Agents Are Morphing Into the 'Enterprise Operating System'

Join our community of newsletter subscribers to stay on top of the news and at the top of your game. 

At Google Cloud Next 2026, Finout co-founder and CEO Roi Ravhon and Google Cloud FinOps lead Pathik Sharma discussed how FinOps is rapidly evolving for the AI era. Ravhon argued that while cloud FinOps had a decade to mature, AI economics are forcing the industry to adapt within a year. Unlike traditional cloud workloads, AI costs are unpredictable because token usage varies even for identical prompts, while advanced reasoning models consume significantly more tokens despite falling prices.

Both emphasized that effective AI FinOps requires intelligent orchestration, routing workloads to the cheapest capable models instead of defaulting to expensive frontier models. Sharma noted that AI costs extend beyond APIs to GPUs, storage, training, and organizational adoption. They also cautioned against relying solely on LLMs for operational automation. Deterministic systems, observability metrics, and human approvals remain essential guardrails. Ultimately, both stressed that FinOps is primarily an organizational and cultural discipline, recommending newcomers start with the FinOps Foundation before investing in tools.

Learn more from The New Stack around the latest in FinOps: 

Why FinOps Isn’t About Saving Money 

FinOps Foundation’s FOCUS 1.2 Expands to SaaS, PaaS 

Join our community of newsletter subscribers to stay on top of the news and at the top of your game. 

Managing Kubernetes at fleet scale introduces significant complexity, especially as organizations expand from a few clusters to hundreds or thousands across cloud, on-premises, and edge environments. While GitOps remains the dominant model for declarative management, its traditional one-to-one repository-to-cluster approach struggles to handle multi-cluster realities such as global traffic routing, shared secrets, and unified observability. AsStephane Erbrech, Principal Software Engineer at Microsoftexplains, the challenge shifts from deployment to governance—maintaining consistency, security, and compliance across a vast distributed system without manual intervention.

This need is amplified by the rise of AI workloads at the edge, where inference is increasingly decentralized. To address these challenges,Microsoft Azure Kubernetes Fleet Managerenables coordinated, staged rollouts across clusters, allowing teams to validate updates in lower-risk environments before production. Supporting this,Cilium Cluster Meshprovides seamless cross-cluster connectivity, enabling workload mobility and efficient resource use, especially for scarce GPU capacity. Together, these tools help modern platform teams manage lifecycle, networking, and orchestration at scale. 

Learn more from The New Stack around managing Kubernetes at fleet scale: 

KubeFleet: The Future of Multicluster Kubernetes App Management

Why Microsoft is betting on temporary identities to stop autonomous agents from going rogue

Join our community of newsletter subscribers to stay on top of the news and at the top of your game. 

In this episode ofThe New Stack Makers, Matthew O’Riordan, CEO of Ably, explains how infrastructure originally built for human collaboration is now well-suited for long-running AI agents. While Ably initially resisted positioning itself as an AI company, the rise of agents that reason, call tools, and operate over extended periods revealed a natural fit for its real-time communication platform.

O’Riordan highlights the limitations of HTTP for these use cases. While effective for short, request-response interactions, HTTP struggles with persistent, stateful experiences—such as handling dropped connections, multi-device usage, or mid-task interruptions. To address this, a new “durable session” layer is emerging, enabling continuous synchronization between agents and users through shared state, presence, and recovery mechanisms.

Ably’s solution, AI Transport, augments existing architectures by keeping HTTP for requests while shifting responses to durable sessions. Features like mutable message streams and “live objects” allow seamless reconnection and collaboration. The goal is to provide a drop-in layer that developers can adopt without rethinking their stack—moving beyond traditional pub/sub models.

Learn more from The New Stack around Ably and AI Transport: 

How MCP Uses Streamable HTTP for Real-Time AI Tool Interaction

Ably Touts Real-Time Starter Kits for Vercel and Netlify

AI Agents Need Help. Here’s 4 Ways To Ship Software Reliably

Join our community of newsletter subscribers to stay on top of the news and at the top of your game. 

Agentic AI is advancing rapidly, with open-source projects racing to keep pace with real-world deployment. To accelerate progress, the Linux Foundation consolidated key technologies—Model Context Protocol (MCP), Goose, and AGENTS.md—under the newly formed Agentic AI Foundation (AAIF) in late 2025. At the MCP Dev Summit in New York City, Linux Foundation CEO Jim Zemlin and newly appointed AAIF executive director Mazin Gilbert discussed this transition. Zemlin explained that leading both organizations was unsustainable, prompting a careful search for a leader with both technical expertise and collaborative leadership skills.

Gilbert now takes on the challenge of guiding AAIF as it shapes the emerging agentic AI ecosystem. While the foundation currently oversees three projects, its broader mission involves defining the future architecture of agent-driven systems—deciding what to build, when, and why. These decisions will influence the trajectory of open-source AI development. The conversation also highlights the importance of open collaboration, funding dynamics, and early adopters in shaping the agentic stack’s evolution.

Learn more from The New Stack around the latest in open-source projects and The Linux Foundation: 

Anthropic Donates the MCP Protocol to the Agentic AI Foundation

SAFE-MCP, a Community-Built Framework for AI Agent Security

Google Donates the Agent2Agent Protocol to the Linux Foundation

Join our community of newsletter subscribers to stay on top of the news and at the top of your game.

Kubernetes is rapidly emerging as the de facto operating system for AI, with two-thirds of organizations using it for generative AI inference and 82% adopting it in production. Its ecosystem — including tools like Kubeflow — enables organizations to build, scale, and retain control of AI systems through open, community-driven infrastructure. Bob Killen of CNCF and Liam Bollmann-Dodd of SlashData shared insights from recent reports showing that AI success still hinges on strong engineering fundamentals—especially internal developer platforms and overall developer experience.

While AI-generated code accelerates development, it shifts bottlenecks to DevOps, reliability, and security, increasing operational complexity. As a result, operator experience and well-defined guardrails have become critical to safely scaling AI. These controls help constrain both human and AI developers, reducing risk while enabling speed. At the same time, organizations are evolving team structures, expanding platform engineering groups to support internal users more effectively. Despite growing complexity, the core lesson remains consistent: open source innovation thrives on people, processes, and collaboration as much as on technology itself.

Learn more from The New Stack around the latest in Kubernetes and its emergence as an operating system for AI: 

Kubernetes and AI: Are They a Fit?

How AI Is Pushing Kubernetes Storage Beyond Its Limits

Kubernetes and AI Are Shaping the Next Generation of Platforms

Join our community of newsletter subscribers to stay on top of the news and at the top of your game. 

In this episode ofThe New Stack Makers,Pete Smailsoutlines howSUSEis evolving from its Linux roots into an AI-native infrastructure platform. Speaking atKubeCon + CloudNativeCon Europe 2026, Smails explains the company’s strategy to unify AI, containers and virtual machines on a single open, enterprise-ready foundation. Central to this isSUSE Rancher Prime, which enables consistent orchestration across hybrid and multi-cloud environments, alongsideSUSE Virtualizationfor modernizing legacy systems.

A key innovation is “Liz,” a context-aware AI agent embedded in Rancher Prime that helps engineers identify vulnerabilities, troubleshoot deployments and interact with infrastructure using natural language. Unlike generic AI tools, Liz understands real-time cluster states and uses Model Context Protocol to deliver actionable insights.

Smails emphasizes developer experience as critical to adoption, highlighting Rancher Developer Access for simplified local Kubernetes workflows. Overall, SUSE aims to deliver secure, automated infrastructure that reduces complexity while accelerating cloud-native and AI adoption.

Learn more from The New Stack around the latest around SUSE: 

SUSE Displays Enhanced Enterprise Linux at SECESSION

SUSE Launches a Sovereign Premium Support Service for EU Customers

Join our community of newsletter subscribers to stay on top of the news and at the top of your game.

In this episode of The New Stack Makers, AWS developer advocate Morgan Willis demonstrates Strands Agents, an open source agentic framework with rapid adoption since its launch. Using a simple accounting API, she walks through three approaches to retrieving a customer’s latest invoice, highlighting how design choices dramatically impact efficiency. The initial method maps each API endpoint to a separate tool, requiring five chained calls and consuming about 52,000 tokens. By shifting to intent-based tools—focused on outcomes rather than individual data operations—the same task is completed in a single call using just 2,000 tokens, improving both efficiency and reasoning.

In a third iteration, tools are hosted on a remote MCP server via AWS Agent Core Gateway, with semantic search limiting the agent’s toolset to only what’s relevant per query, further reducing token usage. Willis emphasizes that narrowly scoped agents outperform general-purpose ones, delivering better speed, accuracy, and context efficiency. Designing smaller, specialized agents with tailored tools is key as tool ecosystems expand.

Learn more from The New Stack around the latest with Strands and MCP:

AWS Launches Its Take on an Open Source AI Agents SDK

What Is MCP? Game Changer or Just More Hype?

MCP’s biggest growing pains for production use will soon be solved

Join our community of newsletter subscribers to stay on top of the news and at the top of your game. 

Broadcom’s VMware Cloud Foundation (VCF) is evolving from a turnkey infrastructure stack into a modern application platform, balancing simplicity with the flexibility demanded by Kubernetes-driven environments. AtKubeCon + CloudNativeCon Europe 2026, Broadcom leaders highlighted how VCF is adapting to support platform engineering teams, cloud-native workloads, and large-scale operations.

A key industry shift is the return to private cloud, driven by data sovereignty concerns and the growing impact of AI. Enterprises are bringing workloads back on-premises while still expecting a cloud-like operating model. Broadcom is responding by prioritizing on-prem stability and aligning closely with open source, reflecting its strong contributions toKubernetesand related projects.

Kubernetes is no longer a bolt-on but the core control plane of VCF, enabling unified management of compute, storage, and networking through declarative APIs. At the same time, the distinction between virtual machines and containers is fading. The focus is shifting toward application-centric platforms, where developers interact through consistent abstractions, allowing infrastructure to be provisioned seamlessly behind the scenes.

Learn more from The New Stack around the latest around Broadcom: 

Broadcom ‘Doubles Down’ on Open Source, Donates Kubernetes Tool to CNCF

Why Broadcom gave Velero to the CNCF Sandbox — and what it means for Kubernetes data protection

Join our community of newsletter subscribers to stay on top of the news and at the top of your game.