AI agents have become capable of reasoning across large amounts of data, calling tools, and taking sequences of actions autonomously. These qualities make them well suited to some of the most persistent pain points in DevOps, including the on-call engineer woken at 3 AM to diagnose an incident, the build failure that takes hours to trace back to a root cause, and the operational toil of modern software delivery. Agentic DevOps is the emerging paradigm that applies these capabilities to the full software lifecycle, with the goal of matching the velocity of modern software delivery with an equally capable operational layer.
Neha Gaswamy leads Agentic DevOps at AWS and has been at Amazon for over twenty years. In this episode, she joins Matt Merrill to discuss the AWS approach to agentic DevOps, how Amazon dogfoods its own DevOps tooling, how their DevOps agent works from alarm to root cause, why determinism still matters in an agentic world, creative MCP integrations customers are building, and what the future holds for SRE engineers as agents take on more of the operational work.
Matt Merrill is a software engineering leader with over 20 years of experience building and scaling software teams across enterprise and product-focused organizations. His background is in backend development, cloud architecture, and distributed systems design. He currently architects and delivers software products and leads a team of engineers at DEPT® Agency. You can learn more about his work at code.theothermattm.com.
Please click here to see the transcript of this episode.
Sponsorship inquiries: sponsor@softwareengineeringdaily.com
The post Agentic DevOps at AWS appeared first on Software Engineering Daily.
AI-generated code is no longer just producing low-quality pull requests. According to AWS Principal Engineer and Valkey core maintainer Madelyn Olson, the quality of AI-assisted contributions has improved dramatically in just the last few months.
In this episode of Screaming in the Cloud, Corey Quinn and Madelyn discuss how AI is changing open source development, the growing burden on maintainers, and how projects like Valkey are using AI to find bugs, improve security, and harden production systems. They also explore Valkey's continued growth, the future of software development, and why experience, operational knowledge, and community still matter in an age where code is becoming cheaper to create.
*Since this episode was recorded without video, we thought it was the perfect opportunity to get creative with AI!
Show Highlights:
(00:00) Open Source Stability Push
(00:32) Reinvent Afterglow Banter
(01:40) AI PRs Get Better
(04:36) Whimsy Versus AI Slop
(06:14) AI Security Hunting Reality
(09:12) Maintainers Adapt to AI
(11:28) Valkey Fork Wins Adoption
(14:43) Fighting the AI Tidal Wave
(23:45) Next Five Years and Roadmap
(27:02) Release Woes and Where to Follow
About Madelyn:
Madelyn Olson is a co-creator and core maintainer of Valkey, a high-performance key-value datastore, and a Principal Engineer at Amazon Web Services (AWS). She specializes in building secure, highly reliable systems and is passionate about collaborating with open-source communities. In her role at Amazon, Madelyn serves as a Principal Software Development Engineer for Amazon ElastiCache and Amazon MemoryDB, where she focuses on advancing distributed data technologies and contributing to the growth and success of the Valkey project.
Sponsored by:
duckbillhq.com
In this two-for-one special recorded at HumanX, Ryan is joined by Dataiku’s Florian Douetteau to chat about the governance, orchestration, and data requirements for serious agentic systems and 1Password’s Nancy Wang for a conversation on making agent swarms secure.
Ryan first catches up with Dataiku co-founder and CEO Florian Douettea to chat serious agentic systems and why they require intentional frameworks, orchestration, governance, and reusable, documented data products. Then, 1Password’s CTO Nancy Wang returns to the show to discuss why current identity standards don’t fit the new world of agents, especially when ephemeral agent swarms make attribution to a single user difficult.
Episode notes:
Dataiku orchestrates data stacks and lets you create analytics, models, and agents.
Florian previously appeared on this program in an episode recorded at the last HumanX conference.
1Password keeps your credentials secure through end-to-end encryption, zero-knowledge architecture, and more. You can learn more about building secure agent swarms at their blog.
Nancy Wang previously appeared on the pod in March 2026.
Connect with Florian on LinkedIn.
Connect with Nancy on LinkedIn.
See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.
Formal methods are a branch of mathematics and computer science focused on proving the correctness of systems, and they have long promised a more rigorous foundation for software. However, their complexity has kept them confined to a small community of specialists. That is now changing as agentic AI systems take on increasingly autonomous roles. The question of how to define, enforce, and verify what those agents are allowed to do has become urgent, and automated reasoning is emerging as a critical part of the answer.
Byron Cook is a VP and Distinguished Scientist at AWS, a professor at University College London, and a program manager at DARPA. He founded the Automated Reasoning Group at AWS over a decade ago, where his team built the foundations behind products like IAM Access Analyzer, VPC Reachability Analyzer, and Bedrock Guardrails.
In this episode, Byron joins Sean Falconer to discuss how automated reasoning works and why it scales so well with AI, the rise of neurosymbolic approaches that combine formal logic with large language models, what it means to formally specify agent behavior using temporal logic, and why the convergence of agentic AI and formal methods may represent one of the most significant shifts in how software is built and verified.
Sean’s been an academic, startup founder, and Googler. He has published works covering a wide range of topics from AI to quantum computing. Currently, Sean is an AI Entrepreneur in Residence at Confluent where he works on AI strategy and thought leadership. You can connect with Sean on LinkedIn.
Please click here to see the transcript of this episode.
Sponsorship inquiries: sponsor@softwareengineeringdaily.com
The post Formal Methods as Agent Guardrails appeared first on Software Engineering Daily.
In this episode, Corey Quinn sits down with AWS Senior Principal Engineer David Yanacek to explore the next evolution of DevOps.
After two decades of building systems to reduce operational pain, David shares how AWS’s new DevOps Agent is pushing automation to a whole new level, autonomously diagnosing incidents, suggesting fixes, and proactively improving systems before engineers even log in.
From pager overload to autonomous remediation, this conversation is a glimpse into a world where software isn’t the bottleneck anymore, operations are evolving into something entirely new.
If you care about DevOps, SRE, platform engineering, or just want fewer 3 a.m. alerts, this episode is for you.
Show highlights:
(00:00) DevOps Meets Agents
(00:13) Welcome and Sponsor Break
(01:29) David Yanacek Backstory
(02:34) DevOps Roots at Amazon
(04:22) DevOps Agent GA Overview
(05:32) LLMs MCP and Any Cloud
(08:32) Guardrails and Safe Changes
(11:47) Beta Results and Consistency
(14:13) Troubleshooting Theory and On Demand
(17:29) Future of DevOps and Closing
About David:
David Yanacek is a Senior Principal Engineer at AWS and a lead advisor on the Agentic AI team. His current work focuses on Kiro, Amazon Bedrock AgentCore, and AWS’s operational agents, where he helps shape the future of intelligent, autonomous systems.
Over a 19+ year career at Amazon and AWS, David has been at the forefront of building services that simplify life for developers and operators. His experience spans serverless, DevOps, and CloudOps, including launching Amazon DynamoDB and AWS IoT Core, and contributing to the direction of cornerstone services like AWS Lambda, Amazon API Gateway, and Amazon CloudWatch.
David also served as the lead publisher for the Amazon Builders’ Library, helping customers apply Amazon’s hard-earned architectural and operational lessons to their own systems.
Outside of engineering, David plays the French horn in a local Seattle ensemble.
Links:
LinkedIn: https://www.linkedin.com/in/david-yanacek/
Website: https://aws.amazon.com/builders-library/authors/david-yanacek/
Sponsored by:
duckbillhq.com
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.
At 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 standard for connecting AI models and agents to tools and data. He explained that MCP’s development is shaped by a diverse group of maintainers who collaboratively prioritize features, balancing major challenges with smaller enhancements that can unlock creative new capabilities. This breadth of perspectives prevents groupthink but makes prioritization difficult, as many ideas compete for limited bandwidth.
Chang highlighted the role of large organizations like Amazon in advancing open source projects. AWS contributions such as Tasks and Elicitations emerged from internal efforts to map cloud services to MCP, revealing gaps in the protocol. Rather than contributing for speed, AWS focuses on real customer use cases, contributing only when clear needs arise. Chang also noted growing demand for MCP servers, while expressing caution about overly specialized, agent-specific implementations that could limit broader interoperability.
Learn more from The New Stack around the latest in Model Context Protocol (MCP) becoming a standard for connecting AI models and agents to tools and data:
Model Context Protocol: A Primer for the Developers
Beyond the vibe code: The steep mountain MCP must climb to reach production
https://thenewstack.io/model-context-protocol-evolution/
Join our community of newsletter subscribers to stay on top of the news and at the top of your game.
At the MCP Summit inNew York City,Clare LiguoriofAmazon Web Servicesdiscussed the rapid rise of theModel Context Protocol(MCP), now a leading way to connect AI agents with tools and data. Originally developed byAnthropicand later transferred to theLinux Foundation, MCP has seen surging enterprise adoption as agentic AI expands.
Liguori highlighted her dual role shaping MCP’s evolving specification, including work on integrating webhooks, events, and notifications to support always-on AI agents. AWS has actively contributed features like Tasks and Elicitations and offers managed MCP servers, positioning itself as both contributor and experimental platform for emerging capabilities.
This collaboration illustrates how corporate involvement can accelerate open-source innovation and adoption. Looking ahead, MCP’s role as connective infrastructure for AI agents is expected to grow, especially as tools become more accessible. With broader adoption of AI development platforms across non-engineering roles, MCP could help extend automation beyond tech teams to businesses of all sizes.
Learn more from The New Stack about the latest around Model Context Protocol(MCP):
MCP: The Missing Link Between AI Agents and APIs
Beyond the vibe code: The steep mountain MCP must climb to reach production
MCP is everywhere, but don’t panic. Here’s why your existing APIs still matter.
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, Jesse Butler, principal product manager for AWS Elastic Kubernetes Service, shares his vision for simplifying cloud-native computing. Since joining AWS in 2020, Butler has focused on making Kubernetes easier to use, emphasizing open-source as a democratizing force. He highlights the role of the Cloud Native Computing Foundation (CNCF) in standardizing and governing open ecosystems while balancing community-driven innovation with commercial contributions.
Butler describes Kubernetes as widely adopted—used in production by around 80% of enterprises—yet still overly complex. His goal is to make it “invisible,” much like Linux, by abstracting and consolidating services. He points to projects like Karpenter, which enables real-time node provisioning for efficient scaling; Kro, which simplifies resource orchestration; and Cedar, a flexible policy engine for fine-grained authorization.
He underscores the importance of open-source contributors, noting their critical yet often underappreciated role. Looking ahead, Butler envisions a future where automation and human collaboration further enhance usability and innovation in open-source software.
Learn more from The New Stack about the latest around AWS Elastic Kubernetes Service
2026 Will Be the Year of Agentic Workloads in Production on Amazon EKS
Amazon EKS Auto Mode wants to end Kubernetes toil — one node at a time
Join our community of newsletter subscribers to stay on top of the news and at the top of your game.
Jon Krohn rounds up March’s interviews in this ICYMI episode. Hear from AI and data science experts across the fields of education and business in this wide-ranging series of clips that take listeners from the Renaissance to the near future. Guests include Lin Quiao (Episode 971), Chris Fregly (Episode 973), Zack Kass (Episode 975), Kyunghyun Cho (Episode 977), and Rohit Choudhary (Episode 979).
Additional materials: www.superdatascience.com/982
Interested in sponsoring a SuperDataScience Podcast episode? Email natalie@superdatascience.com for sponsorship information.
At KubeCon + CloudNativeCon Europe 2026 in Amsterdam, Alex Kestner, principal product manager for Amazon Elastic Kubernetes Service (EKS), discussed how Amazon EKS Auto Mode aims to reduce the operational burden of running Kubernetes at scale. While Kubernetes delivers significant power, it also introduces complexity—particularly through repetitive, day-to-day tasks like managing node lifecycles, ensuring security updates, and selecting optimal infrastructure.
Kestner emphasized that much of this “undifferentiated heavy lifting” distracts platform teams from delivering business value. Amazon EKS Auto Mode addresses this by automating infrastructure operations across the full node lifecycle, shifting responsibility for key operational components outside the cluster and into AWS-managed services.
Built in collaboration with the EC2 team and leveraging technologies like Karpenter, Auto Mode dynamically provisions right-sized compute resources based on workload requirements. While it doesn’t eliminate all challenges—such as unpredictable workloads or diverse deployment needs—it provides a more application-focused approach to scaling and cost optimization. Ultimately, Auto Mode represents a meaningful step toward simplifying Kubernetes operations in increasingly complex cloud-native environments.
Learn more from The New Stack about the latest developments around the latest with Amazon Elastic Kubernetes Service (EKS):
2026 Will Be the Year of Agentic Workloads in Production on Amazon EKS
How Amazon EKS Auto Mode Simplifies Kubernetes Cluster Management (Part 1)
A Deep Dive Into Amazon EKS Auto (Part 2)
Join our community of newsletter subscribers to stay on top of the news and at the top of your game.
Ryan is joined by Nancy Wang, CTO of 1Password, to discuss the security challenges local agents present, how enterprises can create robust governance of credentials through zero-knowledge architecture, and the implications of agent intent and misuse in a world where AI agents are becoming more and more integrated into everyday applications.
Episode notes:
1Password keeps your credentials secure through end-to-end encryption, zero-knowledge architecture, and more. Read their latest white paper on security design.
Connect with Nancy on LinkedIn or email her at nancy.wang@1password.com.
Congratulations to user Binita Bharati for winning a Populist badge for their answer to How to know the version of currently installed package from yarn.lock.
TRANSCRIPT
See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.
Ryan welcomes Gee Rittenhouse, VP of Security at AWS, to the show to discuss the complexities of multi-stage attacks in cybersecurity and how these attacks unfold, the challenges in detecting them, and the evolving role of AI in both enhancing security and creating new vulnerabilities.
Episode notes:
AWS Security Hub is expanding to unify your cloud security options. Learn more about how AWS is keeping your cloud safe on their website.
Connect with Gee on LinkedIn.
Shoutout to user James Kanze for winning a Populist badge for their answer to The spiral rule about declarations — when is it in error?.
TRANSCRIPT
See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.
No one should be manually writing code in 2026, thinks Chris Fregly, Jon Krohn’s guest on this week’s episode. In this interview about Chris’ latest book, AI Systems Performance Engineering, he explains why it’s so important to consider memory bandwidth when evaluating GPU performance, that understanding the full hardware software stack is the most valuable skill for anyone working in AI development, and which shortcuts we still shouldn’t ever take when writing code, even though we might be outsourcing a great deal to generative AI.
This episode is brought to you by the Cisco, by Acceldata and by ODSC, the Open Data Science Conference.
Additional materials: www.superdatascience.com/973
Interested in sponsoring a SuperDataScience Podcast episode? Email natalie@superdatascience.com for sponsorship information.
In this episode you will learn:
(03:39) Why Chris wrote AI Systems Performance Engineering
(21:39) Essential coding metrics
(37:24) The importance of inference when coding
(42:11) How to manage workflows while using AI agents
(51:37) Where and how to invest in the AI market
Jon Krohn recaps the month of February in this episode of In Case You Missed It. Across four interviews with Will Falcon (Episode 965), Tom Griffiths (Episode 969), Antje Barth (Episode 963), and Praveen Murugesan (Episode 967), Jon questions the brains behind some of the AI industry’s most innovative companies about launching a startup, developing a popular product, what artificial intelligence can still learn from human intelligence, and how AI might finally start to think on its own.
Additional materials: www.superdatascience.com/972
Interested in sponsoring a SuperDataScience Podcast episode? Email natalie@superdatascience.com for sponsorship information.
AI-assisted coding tools have made it easier than ever to spin up prototypes, but turning those prototypes into reliable, production-grade systems remains a major challenge. Large language models are non-deterministic, prone to drift, and often lose track of intent over long development sessions.
Kiro is an AI-powered IDE that’s built around a spec-driven development workflow. It’s focused on helping developers capture intent up front, translate it into concrete requirements and designs, and systematically validate implementations through tasks, testing, and guardrails. It aims to preserve the creativity of AI-assisted development while producing software that is ready for real-world use.
David Yanacek is a Senior Principal Engineer and a lead advisor on the Agentic AI team at AWS. Today, his work focuses on Kiro, frontier agents, Amazon Bedrock AgentCore, and AWS’s operational agents. He joins the show with Kevin Ball to discuss the design of Kiro, how spec-driven development changes the way teams work with AI coding agents, and what the next generation of agentic software development might look like.
Kevin Ball or KBall, is the vice president of engineering at Mento and an independent coach for engineers and engineering leaders. He co-founded and served as CTO for two companies, founded the San Diego JavaScript meetup, and organizes the AI inaction discussion group through Latent Space.
Please click here to see the transcript of this episode.
Sponsorship inquiries: sponsor@softwareengineeringdaily.com
The post Amazon’s IDE for Spec-Driven Development with David Yanacek appeared first on Software Engineering Daily.
Bestselling author and Gen AI instructor Antje Barth talks to Jon Krohn about her work at Amazon’s AGI Labs and their newest product Nova Act, as well as where we will see the most success with AI agents and how AI developers can reap those rewards.
This episode is brought to you by the Dell, by Intel, by Fabi and by Cisco.
Additional materials: www.superdatascience.com/963
Interested in sponsoring a SuperDataScience Podcast episode? Email natalie@superdatascience.com for sponsorship information.
In this episode you will learn:
(01:23) Amazon’s latest product, Nova Act
(11:05) How Nova Act tests reliability
(24:01) Where Amazon’s 1000s of gen AI deployments succeed
(31:32) How Nova Act maintains its security
(36:32) The increasing value of agentic AI developers
Marketplace’s Meghan McCarty Carino speaks with Paul Vixie, vice president at AWS Security and an early internet innovator, about the rapid buildout of fiber optic networks during the dot-com boom, and what happened when the bubble burst.
Brought to You By:
• Statsig — The unified platform for flags, analytics, experiments, and more.
• Sonar – The makers of SonarQube, the industry standard for automated code review
• WorkOS – Everything you need to make your app enterprise ready.
—
Amazon S3 is one of the largest distributed systems ever built, storing and serving data for a significant portion of the internet. Behind its simple interfaces hides an enormous amount of engineering work, careful tradeoffs, and long-term thinking.
In this episode, I sit down with Mai-Lan Tomsen Bukovec, VP of Data and Analytics at AWS, who has been running Amazon S3 for more than a decade. Mai-Lan shares how S3 operates at extreme scale, what it takes to design for durability and availability across millions of servers, and why building for failure is a core principle.
We also go deep into how AWS approaches correctness using formal methods, how storage tiers and limits shape system design, and why simplicity remains one of the hardest and most important goals at S3’s scale.
—
Timestamps
(00:00) Intro
(01:03) S3’s scale
(03:58) How S3 started
(07:25) Parquet, Iceberg, and S3 tables
(09:46) S3 for developers
(13:37) Why AWS keeps S3 prices low
(17:10) AWS pricing tiers
(19:38) Availability and durability
(26:21) The cost of S3's consistency
(31:22) Automated reasoning and proof of correctness
(35:14) Durability at AWS scale
(39:58) Correlated failure and crash consistency
(43:22) Failure allowances
(46:04) Two opposing principles in S3 design
(49:09) S3’s evolution
(52:21) S3 Vectors
(1:01:16) The 50 TB limit on AWS
(1:07:54) The simplicity principle
(1:10:10) Types of engineers working on S3
(1:14:15) Closing recommendations
—
The Pragmatic Engineer deepdives relevant for this episode:
• Inside Amazon’s engineering culture
• How AWS deals with a major outage
• A Day in the Life of a Senior Manager at Amazon
• What is a Principal Engineer at Amazon? – with Steve Huynh
• Working at Amazon as a software engineer – with Dave Anderson
Amazon papers recommended by Mai-Lan:
• Using lightweight formal methods to validate a key-value storage node in Amazon S3
• Formally verified cloud-scale authorization
• Analyzing metastable failures
• Amazon’s engineering tenets
—
Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email podcast@pragmaticengineer.com.
Get full access to The Pragmatic Engineer at newsletter.pragmaticengineer.com/subscribe
From the floor at AWS re:Invent, Ryan is joined by AWS Senior Principal Engineer David Yanacek to chat about all things AWS, from the truth behind AWS’s Black Friday origin mythos to the development of essential cloud tools like SQS and DynamoDB. Plus, how David envisions autonomous agents will ease developers' operational burdens.
Episode notes:
This episode was recorded live at AWS re:Invent. Listen to our other episodes from the floor with the Stack Overflow team and Corey Quinn.
Keep up with the latest AWS updates, including what they’re doing with AI, at their site.
Connect with David on Linkedin and Twitter.
TRANSCRIPT
See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.
Kathleen Fisher and Byron Cook dive into automated reasoning and formal verification as tools for building truly secure software systems. PSA for AI builders: Interested in alignment, governance, or AI safety? Learn more about the MATS Summer 2026 Fellowship and submit your name to be notified when applications open: https://matsprogram.org/s26-tcr. They explain how formal methods can harden critical infrastructure against AI-enabled cyberattacks, and how assumptions, specifications, and proofs combine to deliver real security guarantees. The conversation explores using these techniques to train coding models, enable a “great software rewrite,” and power AWS’s new automated reasoning checks for AI agents and policy compliance.
Sponsors:
MATS:
MATS is a fully funded 12-week research program pairing rising talent with top mentors in AI alignment, interpretability, security, and governance. Apply for the next cohort at https://matsprogram.org/s26-tcr
Tasklet:
Tasklet is an AI agent that automates your work 24/7; just describe what you want in plain English and it gets the job done. Try it for free and use code COGREV for 50% off your first month at https://tasklet.ai
Agents of Scale:
Agents of Scale is a podcast from Zapier CEO Wade Foster, featuring conversations with C-suite leaders who are leading AI transformation. Subscribe to the show wherever you get your podcasts
Shopify:
Shopify powers millions of businesses worldwide, handling 10% of U.S. e-commerce. With hundreds of templates, AI tools for product descriptions, and seamless marketing campaign creation, it's like having a design studio and marketing team in one. Start your $1/month trial today at https://shopify.com/cognitive
CHAPTERS:
(00:00) About the Episode
(04:52) AI Reshapes Cybersecurity
(10:16) Formal Methods Foundations
(17:46) Security Properties Assumptions (Part 1)
(21:27) Sponsors: MATS | Tasklet
(24:27) Security Properties Assumptions (Part 2)
(28:31) Helicopter Formal Verification
(38:15) Proof Confidence And AWS (Part 1)
(41:52) Sponsors: Agents of Scale | Shopify
(44:40) Proof Confidence And AWS (Part 2)
(50:33) Automated Reasoning For Policies
(01:04:39) Generative AI Meets Verification
(01:19:42) Securing Future AI Systems
(01:31:19) Agentic Guardrails And Governance
(01:40:44) Outro
PRODUCED BY:
https://aipodcast.ing
SOCIAL LINKS:
Website: https://www.cognitiverevolution.ai
Twitter (Podcast): https://x.com/cogrev_podcast
Twitter (Nathan): https://x.com/labenz
LinkedIn: https://linkedin.com/in/nathanlabenz/
Youtube: https://youtube.com/@CognitiveRevolutionPodcast
Apple: https://podcasts.apple.com/de/podcast/the-cognitive-revolution-ai-builders-researchers-and/id1669813431
Spotify: https://open.spotify.com/show/6yHyok3M3BjqzR0VB5MSyk
<p>What are the advantages of spec-driven development compared to vibe coding with an LLM? Are these recent trends a move toward declarative programming? This week on the show, Marc Brooker, VP and Distinguished Engineer at AWS, joins us to discuss specification-driven development and Kiro.</p>
<p>Marc describes the process of developing an application by writing specifications, which outline what a program should do and what needs it should meet. We dig into a bit of computer science history to explore the differences between declarative and imperative programming.</p>
<p>We also discuss Kiro, a new integrated development environment from Amazon, built around turning prompts into structured requirements. We examine the various types of documents used to specify tasks, requirements, design, and steering. </p>
<div class="alert alert-primary" role="alert">
<p><strong>Real Python Resource Spotlight:</strong> <a href="https://realpython.com/learning-paths/coding-with-ai/">Python Coding With AI - Learning Path</a></p>
<p>Explore tools and workflows for AI in Python: coding partners, prompt engineering, RAG, ChromaDB, FastAPI chatbots, and MCP integrations. Stay current and start today.</p>
</div>
<p>Topics:</p>
<ul>
<li>00:00:00 – Introduction</li>
<li>00:02:41 – How did you get involved in open source?</li>
<li>00:07:23 – How would you describe spec-driven development?</li>
<li>00:10:49 – Balancing the desire to start coding with defining the project</li>
<li>00:13:06 – What does this documentation look like?</li>
<li>00:18:27 – Declarative vs imperative programming</li>
<li>00:24:13 – Infrastructure as part of the design</li>
<li>00:27:03 – Getting started with a small project</li>
<li>00:29:05 – Committing the spec files along with the code</li>
<li>00:31:08 – What is steering?</li>
<li>00:34:17 – How to get better at distilling specifications?</li>
<li>00:38:59 – What are anti-patterns in spec-driven development?</li>
<li>00:41:08 – Should you avoid third-party libraries?</li>
<li>00:43:16 – Real Python Resource Spotlight </li>
<li>00:44:39 – Getting started with Kiro</li>
<li>00:51:00 – Neuro-symbolic AI</li>
<li>00:55:41 – What are you excited about in the world of Python?</li>
<li>00:58:36 – What do you want to learn next?</li>
<li>01:00:18 – How can people follow your work online?</li>
<li>01:00:57 – Thanks and goodbye</li>
</ul>
<p>Show Links:</p>
<ul>
<li><a href="https://kiro.dev/blog/kiro-and-the-future-of-software-development/">Kiro and the future of AI spec-driven software development - Kiro</a></li>
<li><a href="https://brooker.co.za/blog/">Marc Brooker’s Blog - Marc’s Blog</a></li>
<li><a href="https://kiro.dev/">Kiro: The AI IDE for prototype to production</a></li>
<li><a href="https://www.youtube.com/watch?v=OdD9eLiRRVo&t=1s">Beyond Prompts: The Future of AI-Assisted Development | Marc Brooker - YouTube</a></li>
<li><a href="https://martinfowler.com/articles/exploring-gen-ai/sdd-3-tools.html">Understanding Spec-Driven-Development: Kiro, spec-kit, and Tessl</a></li>
<li><a href="https://en.wikipedia.org/wiki/Declarative_programming">Declarative programming - Wikipedia</a></li>
<li><a href="https://cucumber.io/docs/bdd/">Behaviour-Driven Development - Cucumber</a></li>
<li><a href="https://kiro.dev/docs/steering/">Steering - Docs - Kiro</a></li>
<li><a href="https://kiro.dev/docs/specs/best-practices/">Best practices - Docs - Kiro</a></li>
<li><a href="https://kiro.dev/cli/">CLI - Kiro</a></li>
<li><a href="https://kiro.dev/blog/property-based-testing/">Does your code match your spec? - Kiro</a></li>
<li><a href="https://www.fastcompany.com/91446331/amazon-byron-cook-ai-artificial-intelligence-automated-reasoning-neurosymbolic-hallucination-logic">Amazon takes on AI’s biggest nightmare: Hallucinations - Fast Company</a></li>
<li><a href="https://en.wikipedia.org/wiki/Neuro-symbolic_AI">Neuro-symbolic AI - Wikipedia</a></li>
<li><a href="https://marmelab.com/blog/2025/11/12/spec-driven-development-waterfall-strikes-back.html">Spec-Driven Development: The Waterfall Strikes Back</a></li>
<li><a href="https://en.wikipedia.org/wiki/G-code">G-code - Wikipedia</a></li>
<li><a href="https://x.com/MarcJBrooker">Marc Brooker (@MarcJBrooker) / X</a></li>
<li><a href="https://fediscience.org/@marcbrooker">Marc Brooker (@marcbrooker@fediscience.org)</a></li>
<li><a href="https://www.linkedin.com/in/marc-brooker-b431772b/">Marc Brooker - LinkedIn</a></li>
</ul>
<p>Level up your Python skills with our expert-led courses:</p>
<ul>
<li><a href="https://realpython.com/courses/getting-started-claude-code/">Getting Started With Claude Code</a></li>
<li><a href="https://realpython.com/courses/first-steps-langchain/">First Steps With LangChain</a></li>
<li><a href="https://realpython.com/courses/build-neural-network-python-ai/">Building a Neural Network & Making Predictions With Python AI</a></li>
</ul> <p><a rel="payment" href="https://realpython.com/join">Support the podcast & join our community of Pythonistas</a></p>
Nvidia Distinguished Engineer Kevin Klues noted that low-level systems work is invisible when done well and highly visible when it fails — a dynamic that frames current Kubernetes innovations for AI. At KubeCon + CloudNativeCon North America 2025, Klues and AWS product manager Jesse Butler discussed two emerging capabilities: dynamic resource allocation (DRA) and a new workload abstraction designed for sophisticated AI scheduling.
DRA, now generally available in Kubernetes 1.34, fixes long-standing limitations in GPU requests. Instead of simply asking for a number of GPUs, users can specify types and configurations. Modeled after persistent volumes, DRA allows any specialized hardware to be exposed through standardized interfaces, enabling vendors to deliver custom device drivers cleanly. Butler called it one of the most elegant designs in Kubernetes.
Yet complex AI workloads require more coordination. A forthcoming workload abstraction, debuting in Kubernetes 1.35, will let users define pod groups with strict scheduling and topology rules — ensuring multi-node jobs start fully or not at all. Klues emphasized that this abstraction will shape Kubernetes’ AI trajectory for the next decade and encouraged community involvement.
Learn more from The New Stack about dynamic resource allocation:
Kubernetes Primer: Dynamic Resource Allocation (DRA) for GPU Workloads
Kubernetes v1.34 Introduces Benefits but Also New Blind Spots
Join our community of newsletter subscribers to stay on top of the news and at the top of your game.
Kubernetes has relied on role-based access control (RBAC) since 2017, but its simplicity limits what developers can express, said Micah Hausler, principal engineer at AWS, on The New Stack Makers. RBAC only allows actions; it can’t enforce conditions, denials, or attribute-based rules. Seeking a more expressive authorization model for Kubernetes, Hausler explored Cedar, an authorization engine and policy language created at AWS in 2022 and later open-sourced. Although not designed specifically for Kubernetes, Cedar proved capable of modeling its authorization needs in a concise, readable way. Hausler highlighted Cedar’s clarity—nontechnical users can often understand policies at a glance—as well as its schema validation, autocomplete support, and formal verification, which ensures policies are correct and produce only allow or deny outcomes.
Now onboarding to the CNCF sandbox, Cedar is used by companies like Cloudflare and MongoDB and offers language-agnostic tooling, including a Go implementation donated by StrongDM. The project is actively seeking contributors, especially to expand bindings for languages like TypeScript, JavaScript, and Python.
Learn more from The New Stack about Cedar:
Ceph: 20 Years of Cutting-Edge Storage at the Edge
The Cedar Programming Language: Authorization Simplified
Join our community of newsletter subscribers to stay on top of the news and at the top of your game.
AWS’s approach to Elastic Kubernetes Service has evolved significantly since its 2018 launch. According to Mike Stefanik, Senior Manager of Product Management for EKS and ECR, today’s users increasingly represent the late majority—teams that want Kubernetes without managing every component themselves. In a conversation onThe New Stack Makers, Stefanik described how AI workloads are reshaping Kubernetes operations and why AWS open-sourced an MCP server for EKS. Early feedback showed that meaningful, task-oriented tool names—not simple API mirrors—made MCP servers more effective for LLMs, prompting AWS to design tools focused on troubleshooting, runbooks, and full application workflows. AWS also introduced a hosted knowledge base built from years of support cases to power more capable agents.
While “agentic AI” gets plenty of buzz, most customers still rely on human-in-the-loop workflows. Stefanik expects that to shift, predicting 2026 as the year agentic workloads move into production. For experimentation, he recommends the open-source Strands SDK. Internally, he has already seen major productivity gains from BI agents that automate complex data analysis tasks.
Learn more from The New Stack about Amazon Web Services’ approach to Elastic Kubernetes Service
How Amazon EKS Auto Mode Simplifies Kubernetes Cluster Management (Part 1)
A Deep Dive Into Amazon EKS Auto (Part 2)
Join our community of newsletter subscribers to stay on top of the news and at the top of your game.
Major banks once built their own Linux kernels because no distributions existed, but today commercial distros — and Kubernetes — are universal. At KubeCon + CloudNativeCon North America, AWS’s Jesse Butler noted that Kubernetes has reached the same maturity Linux once did: organizations no longer build bespoke control planes but rely on shared standards. That shift influences how AWS contributes to open source, emphasizing community-wide solutions rather than AWS-specific products.
Butler highlighted two AWS EKS projects donated to Kubernetes SIGs: KRO and Karpenter. KRO addresses the proliferation of custom controllers that emerged once CRDs made everything representable as Kubernetes resources. By generating CRDs and microcontrollers from simple YAML schemas, KRO transforms “glue code” into an automated service within Kubernetes itself. Karpenter tackles the limits of traditional autoscaling by delivering just-in-time, cost-optimized node provisioning with a flexible, intuitive API. Both projects embody AWS’s evolving philosophy: building features that serve the entire Kubernetes ecosystem as it matures into a true enterprise standard.
Learn more from The New Stack about the latest in Kube Resource Orchestrator and Karpenter:
Migrating From Cluster Autoscaler to Karpenter v0.32
How Amazon EKS Auto Mode Simplifies Kubernetes Cluster Management (Part 1)
Kubernetes Gets a New Resource Orchestrator in the Form of Kro
Join our community of newsletter subscribers to stay on top of the news and at the top of your game.
At JupyterCon 2025, Jupyter Deploy was introduced as an open source command-line tool designed to make cloud-based Jupyter deployments quick and accessible for small teams, educators, and researchers who lack cloud engineering expertise. As described by AWS engineer Jonathan Guinegagne, these users often struggle in an “in-between” space—needing more computing power and collaboration features than a laptop offers, but without the resources for complex cloud setups.
Jupyter Deploy simplifies this by orchestrating an entire encrypted stack—using Docker, Terraform, OAuth2, and Let’s Encrypt—with minimal setup, removing the need to manually manage 15–20 cloud components. While it offers an easy on-ramp, Guinegagne notes that long-term use still requires some cloud understanding. Built by AWS’s AI Open Source team but deliberately vendor-neutral, it uses a template-based approach, enabling community-contributed deployment recipes for any cloud. Led by Brian Granger, the project aims to join the official Jupyter ecosystem, with future plans including Kubernetes integration for enterprise scalability.
Learn more from The New Stack about the latest in Jupyter AI development:
Introduction to Jupyter Notebooks for Developers
Display AI-Generated Images in a Jupyter Notebook
Join our community of newsletter subscribers to stay on top of the news and at the top of your game.
In an interview at JupyterCon, Brian Granger — co-creator of Project Jupyter and senior principal technologist at AWS — reflected on Jupyter’s evolution and how AI is redefining open source sustainability. Originally inspired by physics’ modular principles, Granger and co-founder Fernando Pérez designed Jupyter with flexible, extensible components like the notebook format and kernel message protocol. This architecture has endured as the ecosystem expanded from data science into AI and machine learning.
Now, AI is accelerating development itself: Granger described rewriting Jupyter Server in Go, complete with tests, in just 30 minutes using an AI coding agent — a task once considered impossible. This shift challenges traditional notions of technical debt and could reshape how large open source projects evolve. Jupyter’s 2017 ACM Software System Award placed it among computing’s greats, but also underscored its global responsibility. Granger emphasized that sustaining Jupyter’s mission — empowering human reasoning, collaboration, and innovation — remains the team’s top priority in the AI era.
Learn more from The New Stack about the latest in Jupyter AI development:
Introduction to Jupyter Notebooks for Developers
Display AI-Generated Images in a Jupyter Notebook
Join our community of newsletter subscribers to stay on top of the news and at the top of your game.
Jupyter AI v3 marks a major step forward in integrating intelligent coding assistance directly into JupyterLab. Discussed by AWS engineers David Qiu and Piyush Jain at JupyterCon, the new release introduces AI personas— customizable, specialized assistants that users can configure to perform tasks such as coding help, debugging, or analysis. Unlike other AI tools, Jupyter AI allows multiple named agents, such as “Claude Code” or “OpenAI Codex,” to coexist in one chat.
Developers can even build and share their own personas as local or pip-installable packages. This flexibility was enabled by splitting Jupyter AI’s previously large, complex codebase into smaller, modular packages, allowing users to install or replace components as needed. Looking ahead, Qiu envisions Jupyter AI as an “ecosystem of AI personas,” enabling multi-agent collaboration where different personas handle roles like data science, engineering, and testing. With contributors from AWS, Apple, Quansight, and others, the project is poised to expand into a diverse, community-driven AI ecosystem.
Learn more from The New Stack about the latest in Jupyter AI development:
Introduction to Jupyter Notebooks for Developers
Display AI-Generated Images in a Jupyter Notebook
Join our community of newsletter subscribers to stay on top of the news and at the top of your game.
What if you had an AI-powered assistant — that took initiative on its own? Technology leader Swami Sivasubramanian believes AI agents are the future of work, capable of sparking new levels of productivity and creativity. Demystifying the workings of autonomous software systems, he explains what they are (and aren’t) and advocates for a world in which AI handles the boring stuff, so you can focus on what matters.
Hosted on Acast. See acast.com/privacy for more information.
