The New Stack Podcast

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.