The New Stack Podcast

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 AWS Strands Agents and Strands Decider to reduce unnecessary memory lookups and keep agent context relevant. While these models offer significant efficiency advantages, Chambers emphasizes the importance of evaluation, monitoring, and human oversight, particularly for high-risk decisions involving financial transactions.

Looking ahead, Chambers envisions a future where developers combine specialized AI models rather than relying exclusively on LLMs, paving the way for more capable, adaptable agents and applications.

Learn more from The New Stack around the latest developments around small decision models and its impact on AI:  

SLMs vs. LLMs: Why Smaller AI Models Win in Business

AWS launches a local answer to TypeSafe’s Jev decision model

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 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 unresolved challenges in agent memory, identity, authentication, observability, and verifying work performed across multiple agents. Surtani also discusses the foundation’s evolving approach to supporting early-stage open-source projects and why the agentic AI stack may never fully stabilize.

Looking ahead, he predicts that AI agents will transform commerce, from purchasing decisions to advertising, making open protocols and industry collaboration increasingly essential.

Learn more from The New Stack around the latest developments around open standards and interoperability in agentic AI: 

The Agentic Web: How AI Agents Are Shaping the Web’s Future

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 rely on AI agents, deterministic workflows, or human oversight. He emphasizes the importance of designing systems that anticipate failures, recover automatically, and provide visibility into every agent action.

Looking ahead, George predicts cheaper AI models, faster processing, and greater adoption of privately deployed agents will accelerate enterprise AI innovation.

Learn more from The New Stack around the latest developments around building mission-critical agentic applications and the infrastructure needed to support them in the AI era:

Why Agentic AI Orchestration Is Key To Managing AI Complexity

A practical systems engineering guide: Architecting AI-ready infrastructure for the agentic era

The rise of agentic AI on Kubernetes: unleashing the new infrastructure layer

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

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.

The conversation explores the foundation’s approach to adopting new open source projects, expanding global participation through partnerships with organizations like the Gates Foundation, and encouraging meaningful community contributions. Gilbert also highlights emerging opportunities in agentic commerce, identity, trust, observability and physical AI.

Looking ahead, the foundation aims to accelerate standardization and expand its global community, ensuring agentic AI systems can scale securely without costly fragmentation.

Learn more from The New Stack around the latest developments around growth of agentic AI and the importance of open standards in shaping its future:

The Architect's Guide to Understanding Agentic AI 

The Agentic Web: How AI Agents Are Shaping the Web's Future 

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

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 retried requests don’t execute twice. Laddad also highlighted Infinity, an open source runtime designed to support massive agent concurrency by suspending idle agents awaiting external operations. Developed jointly by AWS and UC Berkeley, Hydro and Infinity represent efforts to make AI-driven software development more scalable, efficient and trustworthy.

Learn more from The New Stack around the latest developments around front end frameworks:

AI-generated Rust compiles perfectly. That's the scary part. 

Do Frontend Frameworks Still Matter? A Thread 

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

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 interactions, teams can refine tool descriptions, introduce more efficient capabilities and measure improvements through evaluations. Ward also emphasized that MCP isn't always the best integration approach, noting that AWS evaluates alternatives such as command-line interfaces and skills.

Ultimately, Ward advocates applying established software engineering practices to agentic AI: observe workflows, identify problems, test improvements and continuously optimize how humans and AI agents collaborate to accomplish tasks.

Learn more from The New Stack around the latest developments in rapid evolution of developer and agent experiences:

The 3 roles AI agents play in your developer platform

Your agent context needs a development lifecycle 

AWS open-sources an AI agent it says is 45% cheaper than Claude Code and Codex 

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

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 bloat.” AI, however, could help solve some of the complexity it is creating. Estes sees opportunities to use AI automation to monitor Kubernetes clusters, analyze logs, automate infrastructure tasks and potentially predict outages. With tools such as HPE OpsRamp supporting multicloud and on-premises environments, AI-driven operations could ultimately help developers and operations teams manage increasingly complex Kubernetes infrastructure more effectively.

Learn more from The New Stack around the latest developments in HP Enterprise:

HPE's AI agents cut root cause analysis time in half

AI Is Quickly Making IT Teams and Developers From Invisible to Indispensable

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

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 access to increasingly sophisticated AI infrastructure.

AI is now accelerating open-source development itself. CNCF has used agents to assist with project due diligence, helping move projects through its graduation process faster. As AI agents increase development speed and infrastructure demands, Bryce argues that open-source communities will be critical for addressing challenges including multi-cloud computing, hardware diversity, guardrails and software capable of operating at agent speed.

Learn more from The New Stack around the latest open source and AI developments:

Open-source AI is just "4 months behind" closed frontier models - and 10x cheaper 

Is AI killing open-source software? 

Open source maintainers are drowning in AI-generated pull requests. Enterprise teams are next. 

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

Dynatrace's view is that AI apps should be monitored like any other app. They still run alongside older systems, including mainframes, and when something breaks, teams need to know what it cost and why it happened. Their Bluebox agent, introduced in July, compares a team’s code with production data and proposes a fix as a pull request. Engineers can review it or let it run without them. The goal is fewer alerts, delivered in the tools developers already use, such as Claude and Codex, rather than in a separate dashboard.

Learn more from The New Stack around the latest around Dynatrace's latest development:

Dynatrace’s new agents can reveal the single hardest part of AI operations

Beyond automation: Dynatrace unveils agentic AI that fixes problems on its own

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

For many developers, turning an AI-generated prototype into maintainable software requires more than generating code—it requires infrastructure, collaboration, testing and review. In this episode of The New Stack podcast, Bit Cloud founder and CEO Ran Mizrahi discusses Bit Cloud 2.0 and Hope, the company’s AI builder, and how they connect application creation with the work that follows.

Mizrahi explains how reusable components, authentication and integrations can help teams avoid duplicating work, reduce token costs and simplify code review. The conversation also explores collaboration across developers, designers, product managers and business teams, all working from shared building blocks.

Mizrahi demonstrates how development workflows can extend to mobile devices, including staging previews, build checks and code review. The discussion covers working with existing codebases, tools such as Claude Code and Cursor, and moving standard application code beyond Bit Cloud. Demonstrations show an Instagram-style prototype evolving into an application architecture and how testing can catch problems before production. Throughout, Mizrahi emphasizes building on existing work so each application can become a foundation for the next.

Learn more from The New Stack around the latest in integrating AI into Development workflows

Your AI Workflow Is Missing a Composable Architecture

Lessons from 2 Years of Integrating AI into Development Workflows 

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