The New Stack Podcast
by The New Stack
Latest episode
AI agents are getting more complex. Developers shouldn't have to…
AI agents are getting more complex. Developers shouldn't have to…
About this podcast
The New Stack Podcast is all about the developers, software engineers and operations people who build at-scale architectures that change the way we develop and deploy software.
For more content from The New Stack, subscribe on YouTube at: https://www.youtube.com/c/TheNewStack
Episodes
The newest 50 of 300 episodes
- AI agents are getting more complex. Developers shouldn't have to babysit them. · 37 min · Episode 1653AI coding agents are becoming more autonomous, thanks to advances in harness engineering that enable them to identify and correct mistakes before human review. In the latest…
- Beyond LLMs: How Small Decision Models Make AI Agents Smarter and Faster · 33 min · Episode 1652In this episode of The New Stack podcast, recorded at AGNTCon + MCPCon in San Jose, Nick Lucchesi speaks with Mike Chambers, Senior AI Developer Experience Engineer at AWS, about…
- The Future of Agentic AI: Why Open Standards and Interoperability Matter · 24 min · Episode 1651In this episode of The New Stack podcast, recorded at AgentCon + MCPCon in San Jose, host Nick Lucchesi speaks with Manik Surtani, co-founder and CTO of the Agentic AI Foundation…
- Building AI Agents That Don't Fail: Lessons From Orkes · 30 min · Episode 1650Turning a promising AI demo into a reliable, production-ready application requires more than powerful models. At AGNTCon + MCPCon in San Jose, Jeu George, Co-Founder and CEO of…
- Can agent standards keep up with the companies building them? · 25 min · Episode 1649At AGNTCon + MCPCon in San Jose, Mazin Gilbert, executive director of the Agentic AI Foundation, joins The New Stack’s Frederic Lardinois to discuss the rapid growth of agentic…
- AWS's Hydro team wants the compiler to catch coding agents' mistakes · 25 min · Episode 1648As AI agents generate increasingly large volumes of code, traditional code reviews are struggling to keep pace. Shadaj Laddad, research lead for the Hydro team at AWS, believes…
- Why MCP servers should tell agents what to do next · 27 min · Episode 1647James Ward, AWS Fellow and technical committee member of the Agentic AI Foundation, joins The New Stack's Matt Burns at AgntCon+MCPCon 2026 to discuss the rapid evolution of…
- Kubernetes won the orchestration wars. Its teams are still fighting. · 26 min · Episode 1645Kubernetes has become the dominant container orchestration platform, used by more than 80% of container users, but widespread adoption hasn’t eliminated tensions between…
- The CNCF is graduating projects faster than ever. AI agents are helping with the due diligence. · 31 min · Episode 1644Open-source technology has played a foundational role in the AI boom, giving companies the flexibility to scale unprecedented computing workloads across providers and hardware…
- Dynatrace wants its AI agents to fix problems instead of adding alerts · 20 min · Episode 1643Dynatrace sells software that monitors companies’ apps and infrastructure and wants its AI agents to make engineers’ jobs easier. An agent that gets in the way is a bad agent and…
- Bit Cloud’s next chapter starts after the AI builds your app · 31 min · Episode 1641For many developers, turning an AI-generated prototype into maintainable software requires more than generating code—it requires infrastructure, collaboration, testing and…
- CloudBees just committed to an AI-first pivot. Here's why it matters for enterprise DevOps teams · 24 min · Episode 1642CloudBees CEO Mo Plassnig is leading the CI/CD company through a major transformation as generative AI reshapes software development. Returning to CloudBees eight years after…
- A third option is emerging in the fight over AI and your data · 31 min · Episode 1640The AI industry has faced a growing enterprise dilemma: companies want access to powerful proprietary AI models without risking sensitive data or intellectual property, while AI…
- Drowning in AI pull requests: Harness's field CTO on code review and a Git repo built for agents · 26 min · Episode 1639Harness Field CTO Martin Reynolds joins The New Stack to talk about what happens after coding agents start opening pull requests faster than anyone can review them. He explains…
- How to find failures without drowning in tracing data · 31 min · Episode 1638Traces provide a detailed view of a request’s journey through data, microservices and applications, helping SREs pinpoint where failures occur and resolve issues faster. But…
- Why CPUs still matter in the age of AI agents · 26 min · Episode 1637As AI evolves from conversational chatbots to autonomous agents, CPUs are becoming an increasingly important part of the infrastructure equation. In this episode, The New Stack…
- Why Doist Says Less AI Can Deliver More · 36 min · Episode 1636Doist CTO Gonçalo Silva says AI is reshaping software development, but success depends on restraint rather than rapid feature expansion. Instead of chasing every AI capability…
- Why your company should (try to) build its own AI SRE · 30 min · Episode 1635As AI coding agents accelerate software development, they also create new challenges for site reliability engineers (SREs), who are increasingly responsible for debugging systems…
- Nvidia · 33 min · Episode 1634In this episode with The New Stack's Frederic Lardinois, NVIDIA’s Joey Conway says advances in AI over the past year have dramatically improved the capabilities of local models…
- Meet Brain, the AI that decides when Azure is officially down · 19 min · Episode 1633In this episode, Mark Russinovich, CTO of Microsoft Azure revealed Brain, the AI-powered AIOps system that continuously monitors Azure’s health, detects incidents, identifies…
- What comes after attention? This startup says it already knows. · 20 min · Episode 1632Subquadratic is beginning to back up its ambitious claims with benchmarks and third-party validation for its SubQ 1.1 Small model, which uses its proprietary Sparse Attention…
- “The harness is where the hard work is”: Harness bets on agents that enterprises can trust in production · 20 min · Episode 1631Harness has introduced Autonomous Worker Agents, a new capability that allows enterprises to replace rigid CI/CD pipeline scripts with AI agents that can deploy applications, run…
- Public cloud vs. on-prem: Summit on where each workload belongs · 37 min · Episode 1630More than two decades after AWS helped usher in the public cloud era, many organizations are reassessing whether a cloud-first strategy still delivers the cost and operational…
- Gusto Cofounder: An AI agent that runs payroll, HR, and benefits without waiting to be asked · 29 min · Episode 1629Gusto is betting that small businesses need more than another AI assistant. The company’s new product, Gusto Cofounder, is designed to act as a proactive business partner that…
- WeAreDevelopers is coming to the US to give unsung developers a bigger voice · 50 min · Episode 1628WeAreDevelopers, the Berlin-based developer conference founded in 2015, has grown into a major global event, attracting 15,000 developers from over 70 countries each year. In…
- Why MotherDuck refuses to fork DuckDB · 28 min · Episode 1625At a recent MCP developer summit, The New Stack spoke with Till Döhmen, AI lead at MotherDuck, about the company’s growing role in the evolving DuckDB ecosystem. Backed by…
- JetBrains is selling independence as the rest of AI coding picks sides · 26 min · Episode 1626JetBrains is positioning itself as the last major independent AI coding-tool vendor in a market increasingly tied to hyperscalers and foundation model labs. Speaking at Google…
- Why Block handed Goose to the Linux Foundation · 20 min · Episode 1624What began as an internal developer tool at Block has evolved into a broader open-source initiative with industry backing. Goose, Block’s AI coding agent, followed a path similar…
- Fivetran's CPO: closed data stacks won't survive the agent era · 23 min · Episode 1623At 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…
- The new FinOps problem isn't cloud bills · 28 min · Episode 1621At 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…
- How Microsoft is governing thousands of Kubernetes clusters without manual intervention · 25 min · Episode 1620Managing Kubernetes at fleet scale introduces significant complexity, especially as organizations expand from a few clusters to hundreds or thousands across cloud, on-premises…
- Why long-running AI agents break on HTTP and how Ably is fixing it · 32 min · Episode 1618In 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…
- Why the Linux Foundation adopted MCP, with Jim Zemlin and Mazin Gilbert · 33 min · Episode 1619Agentic AI is advancing rapidly, with open-source projects racing to keep pace with real-world deployment. To accelerate progress, the Linux Foundation consolidated key…
- Fresh data has us asking, does AI demand Kubernetes? · 23 min · Episode 1617Kubernetes 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…
- How SUSE positions itself as the infrastructure layer for the AI era · 27 min · Episode 1616In this episode of The New Stack Makers, Pete Smails outlines how SUSE is evolving from its Linux roots into an AI-native infrastructure platform. Speaking at KubeCon +…
- Cut AI token usage by 96%? Here’s how AWS Strands Agents does it. · 28 min · Episode 1615In 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…
- Why Broadcom is betting on a private cloud comeback · 24 min · Episode 1614Broadcom’s VMware Cloud Foundation (VCF) is evolving from a turnkey infrastructure stack into a modern application platform, balancing simplicity with the flexibility demanded by…
- Why Broadcom gave Velero to the CNCF Sandbox — and what it means for Kubernetes data protection · 23 min · Episode 1612Broadcom continues to expand its role as a major contributor to cloud-native open source, particularly within the Cloud Native Computing Foundation (CNCF) ecosystem. Its recent…
- Why AI engineering needs old-school discipline · 24 min · Episode 1611In this episode of The New Stack Makers, Nimisha Asthagiri of ThoughtWorks explores why many AI initiatives stall between proof of concept and production. A key issue is that…
- Jim Bugwadia on why finding a Kubernetes problem is only half the battle for Kyverno users · 23 min · Episode 1610Graduating within the CNCF marks a major milestone for an open source project, signaling not just technical maturity but strong governance, security practices, and widespread…
- How AWS Bedrock is shaping Model Context Protocol · 31 min · Episode 1609At the MCP Summit in New York City, AWS’s Luca Chang, a Bedrock team member and MCP specification maintainer, discussed the rapid rise of the Model Context Protocol (MCP) as a…
- Why Microsoft is betting on temporary identities to stop autonomous agents from going rogue · 25 min · Episode 1608At KubeCon Europe 2026, Jorge Palma outlined how Microsoft is advancing AI operations across cloud and edge environments. He demonstrated an agent capable of diagnosing…
- As agentic AI explodes, Amazon doubles down on MCP · 24 min · Episode 1607At the MCP Summit in New York City, Clare Liguori of Amazon Web Services discussed the rapid rise of the Model Context Protocol (MCP), now a leading way to connect AI agents with…
- A year in, Google wants its Axion processors to feel like a scheduling decision · 22 min · Episode 1606At KubeCon Europe, Google Cloud’s Jago Macleod and Abdel Sghiouar argued that adopting Arm for Kubernetes workloads has shifted from a complex migration to a practical…
- Can you make Kubernetes invisible? Here's why AWS is on a mission to do it. · 23 min · Episode 1605In this episode of The New Stack Makers, Jesse Butler, principal product manager for AWS Elastic Kubernetes Service, shares his vision for simplifying cloud-native computing…
- The next stages of AI conformance in the cloud-native, open-source world · 25 min · Episode 1604Running AI models on Kubernetes has historically been inconsistent, with workloads behaving differently across cloud providers due to variations in GPUs, networking, and…
- Microsoft wants to make service mesh invisible · 21 min · Episode 1603At KubeCon EU 2026, Mitch Connors of Microsoft outlined a vision to make service meshes effectively invisible to users. Now working on Azure Kubernetes Application Network, a…
- Amazon EKS Auto Mode wants to end Kubernetes toil — one node at a time · 23 min · Episode 1602At KubeCon + CloudNativeCon Europe 2026 in Amsterdam, Alex Kestner, principal product manager for Amazon Elastic Kubernetes Service (EKS), discussed how Amazon EKS Auto Mode aims…
- Edge-forward: Akamai eyes sweet spot between centralized & decentralized AI inference · 22 min · Episode 1601At KubeCon + CloudNativeCon Europe 2026, Lena Hall and Thorsten Hans of Akamai outlined how the company is evolving from a CDN provider into a developer-focused cloud platform…
- Kubernetes co-founder Brendan Burns: AI-generated code will become as invisible as assembly · 44 min · Episode 1598In this episode of The New Stack Makers, Microsoft Corporate Vice President and Technical Fellow, Brendan Burns discusses how AI is reshaping Kubernetes and modern…
