earuphoria.
All podcasts
News · Technology

The New Stack Podcast

The New Stack
Rights holder? Report thisthenewstack.simplecast.com

Episodes

November 19, 2026 · Episode 1663

GPUs are scarce. Here's how AWS is making every GPU count.

As demand for GPUs continues to outpace supply, maximizing the efficiency of existing capacity has become a critical challenge for AI developers. In this episode of The New Stack Podcast, recorded at KubeCon + CloudNativeCon North America 2026 in Salt Lake City, host Matt Burns speaks with Sagin from Amazon Web Services (AWS) about new capabilities in Amazon EKS designed to optimize GPU utilization and support emerging AI workloads. Sagin discusses AWS's latest enhancements to EKS Auto Mode and Karpenter, including capacity reservations and Dynamic Resource Allocation (DRA), which improves GPU scheduling and communication efficiency. He also explores techniques...

November 18, 2026 · Episode 1662

Why AI Agents Need a New Approach to Observability

As AI workloads become increasingly complex, observability must evolve beyond traditional logs, metrics, and traces to provide developers with the context needed to understand and manage applications. In this episode of The New Stack Podcast, recorded at KubeCon + CloudNativeCon 2026 in Salt Lake City, Sean O'Dell of Dynatrace joins Frederic Lardinois to discuss the future of full-stack observability and AI-driven development. O'Dell explains why OpenTelemetry remains foundational to modern observability, including its expanding role in monitoring AI agents and models. He also explores how OpenFeature and feature flagging enable progressive delivery, faster troubleshooting, and safer experimentation across cloud...

November 17, 2026 · Episode 1661

Why groundcover's CEO says agents are the power users of observability

Observability is entering a new era as AI agents transform how developers build, monitor, and operate software. In this episode of The New Stack Podcast, recorded at KubeCon + CloudNativeCon 2026 in Salt Lake City, Frederic Lardinois speaks with Shahar, CEO and co-founder of groundcover, about the evolution of AI-native observability and the path toward autonomous operations. Shahar explains how traditional observability tools are struggling to keep pace with increasingly complex AI workloads, where agents can execute thousands of tool calls across hours of activity. Groundcover addresses these challenges through its bring-your-own-cloud architecture, eBPF-based monitoring, and AI-powered capabilities that...

November 16, 2026 · Episode 1660

AI agents were all over KubeCon. Production is another story

At KubeCon + CloudNativeCon North America 2026 in Salt Lake City, The New Stack’s Frederic Lardinois sat down with Jonathan Bryce, executive director of the Cloud Native Computing Foundation (CNCF), to discuss how AI is reshaping cloud native infrastructure, open source innovation, and the developer community. Bryce explains why Kubernetes and cloud native technologies are becoming increasingly essential as AI agents introduce workloads that demand greater scalability, resilience, and efficiency. He highlights new CNCF projects, including Open Shell and Agent Substrate, alongside llm-d, which aim to improve AI security, resource utilization, and infrastructure performance while addressing growing concerns ab...

November 16, 2026 · Episode 1659

DuckDB 2.0 goes client-server and adds an Agent Mode for coding agents

DuckDB is entering a new era following AWS’s acquisition of DuckLabs and the release of DuckDB 2.0.0, its biggest feature update to date. In this episode of The New Stack Podcast, Gábor Szárnyas, developer advocate at DuckLabs, discusses how the high-performance analytical database is evolving to support AI agents, faster queries, and more flexible data processing. The release introduces significant enhancements, including server capabilities, an extensible SQL parser, the Quack remote protocol, and a dedicated Agent Mode. Designed for AI coding agents, Agent Mode delivers compact Markdown tables, machine-readable errors, and token-saving optimizations that help agen...

November 14, 2026 · Episode 1658

DuckDB has an answer to “bloated” database messages

DuckDB is rethinking how databases communicate with the launch of Quack 1.0, a production-ready, HTTP-based client/server protocol designed for faster, more efficient analytical workloads. In this episode of The New Stack Podcast, Guillermo Sánchez Dionis, product lead at DuckLabs, explains how Quack addresses the limitations of traditional database protocols, which often introduce unnecessary overhead and inefficient data serialization. Unlike conventional protocols built around row-based data transmission, Quack leverages DuckDB’s columnar data representation and vectorized execution engine to deliver faster, more efficient query results. Its streaming architecture allows clients to consume results as they are generated, sig...

November 13, 2026 · Episode 1657

DuckLake 1.1 solves the absurd complexity of data lakes at AI scale

DuckLake is simplifying data lakehouse management by replacing complex metadata files with a familiar SQL-based approach. In this episode of The New Stack Podcast, Pedro Holanda, lead DuckLake developer and principal engineer at DuckLake, discusses how the open-source table format reduces complexity, improves performance, and makes large-scale data management more accessible. With the release of DuckLake 1.1 alongside DuckDB 2.0.0 LTS, Holanda explains how storing metadata in a relational database eliminates the need to navigate countless files to locate and query data. By combining Parquet storage with SQL catalogs, DuckLake streamlines data access while addressing common challenges such as...

November 13, 2026 · Episode 1646

The Context Problem: What's Really Breaking AI Agents at Scale

As AI models become more powerful and affordable, enterprises still face a major obstacle to realizing the full potential of AI agents: the context gap. Without access to accurate, relevant information, even the most advanced models struggle to deliver meaningful results. In this episode of The New Stack podcast, Sri Desikan, an executive at Elastic, explains why providing AI agents with the right context is essential for moving beyond impressive demonstrations to reliable enterprise automation. Simply connecting agents to enterprise data through MCP servers isn't enough. Feeding massive amounts of information into large language models is...

November 11, 2026 · Episode 1656

The Next Essential Developer Skill: Building AI Agents

As AI agents transform software development, developers face a fundamental shift in the skills they need to succeed. In this episode of The New Stack podcast, recorded at AGNTCon and MCPCon in San Jose, Frederic Lardinois speaks with Angie Jones, Vice President of the Agentic AI Foundation, about the evolving developer role and the challenges of adopting AI across engineering organizations. Drawing on her experience leading AI enablement at Block, Jones explains how embedding agent-friendly practices into development workflows helped drive widespread adoption. She emphasizes the growing importance of system design, logical thinking, and building agentic systems ra...

November 10, 2026 · Episode 1655

New CNCF report: 75% of cloud-native developers ship code with AI. Jonathan Bryce explains why.

AI adoption is accelerating among cloud-native developers, who are leading the charge in integrating artificial intelligence into software development. According to the Cloud Native Computing Foundation’s (CNCF) Q3 2026 State of Cloud Native Development report, 21.2 million developers—41% of the global developer population—work with cloud-native technologies. Of those, 75% use AI to write and ship code, compared with just 50% of non-cloud-native developers. In this episode of The New Stack podcast, CNCF Executive Director Jonathan Bryce discusses the rapid growth of the cloud-native ecosystem, evolving developer trends, and the expanding role of open source in driving innovation. Bryce...

November 9, 2026 · Episode 1654

Why Agentic AI Needs a New Approach to Data Infrastructure

As AI agents transform how businesses access and process data, traditional siloed infrastructure is struggling to keep pace. In this episode of The New Stack podcast, recorded at AGNTCon + MCPCon 2026, Frederic Lardinois speaks with Bianca Lewis, Executive Director of the OpenSearch Software Foundation, about why unified, open source data infrastructure is becoming essential for agentic AI. Lewis explains how OpenSearch is evolving beyond traditional search and observability into an AI data infrastructure platform that enables organizations to scale workloads, reduce costs, maintain data sovereignty, and avoid vendor lock-in. The conversation explores how AI agents introduce ne...

November 6, 2026 · Episode 1653

AI agents are getting more complex. Developers shouldn't have to babysit them.

AI 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 episode of The New Stack podcast, Vanitha Kumar, Principal Technologist at Thoughtworks, explains how automated tests, feedback loops, and guardrails allow agents to handle longer running tasks with less human intervention while working in parallel. Kumar also explores the rise of AI factories, which provide standardized infrastructure for model selection, workload management, and cost optimization. Much like Kubernetes simplified microservices management, AI factories aim to make deploying and managing AI agents easier at scale. However, greater autonomy introduces security risks as agents ga...

November 4, 2026 · Episode 1652

Beyond LLMs: How Small Decision Models Make AI Agents Smarter and Faster

In 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 how small decision models could make AI agents faster, more efficient, and cost-effective. Unlike large language models (LLMs) that generate responses through multiple processing steps, decider models quickly evaluate information and return probability-based decisions. Chambers explains how these models can improve agent performance by routing requests to appropriate LLMs, enforcing safety guardrails, and determining when agents should retrieve information from memory. He also shares experiments using...

November 3, 2026 · Episode 1651

The Future of Agentic AI: Why Open Standards and Interoperability Matter

In 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 (AAIF), about the growing importance of open standards, interoperability, and vendor-neutral governance in agentic AI. With 305 member organizations and 10 projects, AAIF is expanding its ecosystem through new additions including Anthropic’s AgentSkills, OpenAI’s OpenResponses, Hugging Face’s OpenM, and Alibaba’s OpenSandbox. Surtani explains how these projects help developers build more portable, trustworthy AI systems while reducing dependence on individual vendors. The conversation explores unresolv...

November 3, 2026 · Episode 1650

How Orkes ParticleDB turns an impressive demo into a remarkable application

Turning 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 Orkes, joins The New Stack’s Nick Lucchesi to discuss the challenges of building mission-critical agentic applications and the infrastructure needed to support them. George explains how Orkes Conductor helps developers orchestrate AI agents, manage failures, enforce security guardrails, and maintain audit trails for accountability and compliance. He also introduces ParticleDB, an agentic database designed to simplify enterprise data access while keeping sensitive information within company cloud environments. Using examples from financial services and e-commerce, George explores when businesses should r...

October 30, 2026 · Episode 1649

Can agent standards keep up with the companies building them?

At 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 AI and the importance of open standards in shaping its future. With 4,300 conference registrants and a rapidly expanding membership, the foundation is bringing together technology giants, startups, nonprofits and enterprises to address challenges around scalability, security, interoperability and governance. Gilbert explains how protocols like MCP are fueling a new economy of startups while enabling competing companies, including OpenAI, Anthropic, Google and Microsoft, to collaborate on shared infrastructure. ...

October 29, 2026 · Episode 1648

AWS's Hydro team wants the compiler to catch coding agents' mistakes

As 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 the solution lies in automated correctness checks that operate outside an AI agent’s control. Speaking at AGNTCon + MCPCon, Laddad explained how Hydro, an open source Rust framework for distributed systems, uses compile-time checks to catch bugs before code runs. Inspired by Rust’s borrow checker, Hydro aims to provide shared, domain-specific guardrails that help developers maintain reliability even as agents produce larger, more complex code changes. The team is also exploring safeguards for recurring challenges such as idempotency, ensuring ret...

October 28, 2026 · Episode 1647

Why MCP servers should tell agents what to do next

Many Model Context Protocol (MCP) servers function as basic APIs, returning data without guiding AI agents on what to do next. AWS Principal Developer Advocate James Ward believes MCP servers should play a more active role in agent workflows, providing context, recommendations and actionable next steps. Speaking at AGNTCon + MCPCon in San Jose, Ward explained how better observability and evaluation can improve agent performance. Because MCP lacks built-in trace IDs, AWS uses session identifiers to track tool calls across workflows, helping developers understand how agents interpret requests, identify inefficiencies and complete tasks. By analyzing these...

October 7, 2026 · Episode 1645

Kubernetes won the orchestration wars. Its teams are still fighting.

Kubernetes has become the dominant container orchestration platform, used by more than 80% of container users, but widespread adoption hasn’t eliminated tensions between developers and operations teams. Developers value Kubernetes for its self-service capabilities and ability to move quickly, while operations teams prioritize stability, governance and controlled change. In this episode, HPE Fellow David Estes explains how those competing priorities are becoming more challenging as applications spread across hybrid and edge environments and AI inference workloads increase demand for GPU scheduling and rapid capacity scaling. He also warns that excessive reliance on microservices can create unnecessary “architecture bloa...

October 6, 2026 · Episode 1644

The CNCF is graduating projects faster than ever. AI agents are helping with the due diligence.

Open-source technology has played a foundational role in the AI boom, giving companies the flexibility to scale unprecedented computing workloads across providers and hardware. OpenAI, for example, used Kubernetes as early as 2018 to balance compute across its own data centers, AWS and Azure — years before ChatGPT brought generative AI into the mainstream. CNCF Executive Director Jonathan Bryce sees a powerful feedback loop emerging between AI and open source. Early AI companies relied on open-source tools because commercial products couldn’t support the scale and complexity of their work. As those companies contribute back, enterprises across industries gain acce...

Similar podcasts