Screaming in the Cloud

What happens when AI agents become the primary users of the cloud?
In this live episode of Screaming in the Cloud, Corey Quinn sits down with Cloudflare's Dane Knecht and Rita Kozlov at Cloudflare Connect to discuss how AI is changing the way developers build, deploy, and manage applications.

They explore Cloudflare's evolution from its networking roots into a full developer platform, why traditional cloud infrastructure struggles to keep up with AI agents, and how tools like Cloudflare's CF CLI are making development more accessible.

The conversation also tackles the realities of AI-assisted coding, the importance of human judgment when deploying to production, and the growing debate over building versus buying software. Plus, they discuss what happens when bots become a major part of internet traffic and how businesses may need to rethink access, security, and monetization.

With Corey's signature humor and plenty of candid insights, this episode offers a look at how Cloudflare is preparing for an internet increasingly built for both humans and AI agents.

About Dane Kozlov and Rita Kozlov :

Dane Knecht is the Chief Technology Officer at Cloudflare, the leading connectivity cloud company. Knecht is responsible for bringing the company’s most audacious and innovative ideas to life that will be key to Cloudflare’s ongoing evolution and strategy. Over the last 13 years at Cloudflare, he has led the development, launch, and scaling of products like Cloudflare Zero Trust, Cloudflare’s Developer Platform, and most recently, the company’s AI inference and agents platform. Knecht joined Cloudflare when the company had fewer than 30 people. Prior to Cloudflare, Knecht founded an ecommerce SaaS company, which was later acquired, and held product leadership roles at MessageOne and Dell. He graduated from Columbia University and resides in Austin, Texas.

RIta Kozlov is VP of Product for Cloudflare’s developer platform, where she leads the work behind the tools and runtime developers use to build globally distributed applications and AI-powered systems. Her scope spans Cloudflare Workers, Durable Objects, and the execution, security, and coordination layers that help make stateful and agentic software dependable at scale.

Show Highlights:

(00:00) Judgment Over Rules
(00:30) Meet the Guests
(01:14) What Cloudflare Does
(02:13) From CDN to Platform
(03:43) Building for Agents
(06:48) CF CLI and Agent UX
(13:31) AI Principles No Vibes
(22:58) Autonomy Incidents Codex
(31:25) Build vs Buy Personal Tools
(35:56) Dead Internet and Agent Future

Sponsored by:
duckbillhq.com

Corey Quinn sits down with Pasquale DeMaio, VP of Amazon Connect Customer , to talk about how Agentic AI is reshaping customer service, and why replacing humans isn’t necessarily the goal. They dig into the evolution of Amazon Connect Customer from a cloud-based contact center into an AI-powered customer experience platform, where agentic AI, real-time customer context, voice technology, and deterministic workflows work together to actually solve problems.

They also explore where humans still matter most, why poorly chosen metrics can create terrible customer experiences, the importance of guardrails as AI becomes more autonomous, and what happens when AI agents start talking to other AI agents. The future of customer service may be increasingly automated, but the real opportunity is making every interaction feel smarter, faster, and more human.

Show Highlights: 

(00:16) Origin Story of Connect

(01:49) From Call Center to Cloud

(04:48) AI First Engagement Vision

(07:04) Agentic Canvas and Workflows

(09:20) When AI vs Humans Matter

(11:20) Guardrails and Fraud Risks

(14:11) Multimodal Live Sync Flights

(16:35) New Voices and Localization

(18:18) Voice Selection and Custom Voices

(20:49) Enterprise Scale and Trust

(23:45) A2A and Open Agent Ecosystem

(25:21) Making Connect Easier to Use

(27:53) Customer Profiles and Personalize

(29:20) Wrap Up and Where to Learn More

Sponsored by:
duckbillhq.com

What happens when open source, AI, and decades of database technology collide?

Corey Quinn sits down with German Eichberger, Principal AI Engineering Manager at Microsoft, to dig into DocumentDB, why it’s built on PostgreSQL, and the realities of MongoDB compatibility. They explore how Kubernetes and databases have evolved to better support stateful workloads, why MCP servers could give AI agents safer database access, and how AI may dramatically increase the number of databases organizations need to manage.

Show Highlights: 

(0:00) Databases in Volatile Environments

(00:12) Welcome and Introductions

(01:20) AI Titles and Pay Signals

(02:53) Why DocumentDB Exists

(05:04) Mongo API on Postgres

(07:15) No Forking Postgres

(08:09) Compatibility and Standards

(12:12) Governance and Roadmap

(15:15) Kubernetes and MCP Agents

Sponsored by:
duckbillhq.com

AWS Morning Brief for the week of September 14th with Corey Quinn. 

Links:

• Amazon API Gateway now supports 1 MB execution logs with configurable delivery destinations
• Amazon S3 Object Lock now supports variable retention with event holds
• Lambda's slow-motion reinvention of EC2
• Amazon EC2 now supports specifying compatible instance types on AMIs
• Announcing second-generation single-rack AWS Outposts
• How AWS thinks about FinOps Automation and Trust
• Introducing Amazon EBS Volume Clones across AWS accounts
• How to migrate from Amazon CloudSearch to Amazon OpenSearch Serverless
• Introducing Pizza Bot, an open source inbox for AI agents that work in the background
• Three consecutive CVEs, all AWS-authored code

AWS VP of Global Networking Matt Rehder joins Corey Quinn to pull back the curtain on the massive network infrastructure behind AWS. They explore resiliency at scale, AWS’s move toward flatter networks, the advantages of building custom hardware, and why AI is making networking exciting again.

Show Highlights: 

(01:08) Meet AWS Networking Lead

(02:01) Why AWS Avoids Global Outages

(05:23) RNG Flat Network Explained

(10:08) Overbuild Capacity And Custom Hardware

(17:37) VPC Virtual Network Origins

(19:50) Why TCP Still Wins

(20:38) SRD Inside AWS

(21:54) Opt In SRD Transport

(25:31) Networks As Utilities 

(27:24) Learning And Growing Engineers

(29:22) Training Talent In House

(31:27) AI Rekindles Networking

(34:26) Where To Learn Networking

Sponsored by:
duckbillhq.com

On this episode of Screaming in the Cloud, Corey Quinn sits down with Adam Larsen, Principal Developer at Aurora Educational Technologies, to explore what technology and AI should actually look like in K-12 education. They discuss using tech to empower teachers rather than replace them, the risks of outsourcing critical thinking to AI, student data privacy, and what happens when schools become dependent on tools that may not be affordable forever. Adam also shares how AWS became his go-to platform for solving complex education data problems, and why sometimes the best technology is simply the one that reliably gets the job done.

Show Highlights: 

00:00 Critical Thinking Warning

00:15 Meet the Guest

01:07 From Psych to Edtech

02:07 Teachers and Tool Whiplash

07:29 AI as a Teaching Aid

10:07 Process Over Shortcuts

14:29 Tech Misconceptions in Schools

16:38 Privacy and Picking Vendors

21:50 AI Costs and Ecosystem Bets

26:33 Building on AWS and Wrap Up

Sponsored by:
duckbillhq.com

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

What happens when two cloud economists leave AWS  behind and spend six days hiking 60 miles on the Appalachian Trail? Corey Quinn sits down with Caleb Hurd to share stories from the trail, including exploding sleeping pads, heroic shuttle drivers, lost phones, and the unique community that makes long-distance hiking special. Along the way, they draw surprising parallels between backpacking and cloud economics, discussing everything from serverless architecture and cloud cost optimization to the hidden challenges of on-prem infrastructure. It's a conversation about technology, adventure, perspective, and why sometimes the best way to solve complex problems is to step away from them entirely.

Show highlights:

(00:00) Why Hiking Hooks You
(00:15) Meet Caleb on the Trail
(01:31) Trail Miles and Ultralight Parallels
(05:24) The Sleeping Pad Blowout
(07:46) Shepherd Saves the Day
(09:43) Trail Community and Cloud Community
(11:07) Post Trail Perspective and Inside Jokes
(15:35) Back to Work On Prem vs Cloud Pain
(25:47) Server-less Spend and Lambda Sprawl
(32:29) Wrap Up Where to Find Caleb

About Caleb:
Caleb Hurd is a Cloud Economist at Duckbill, where he helps enterprises make sense of their cloud spend. Before moving to the cost side of the house, Caleb spent years in the trenches building and operating large-scale cloud environments and leading the engineering teams behind them across companies ranging from healthcare tech to enterprise Saas. He also founded CostOps.cloud, an AWS cost consulting practice, and is a vocal advocate for engineering-led FinOps — arguing that the people closest to the architecture should be the ones driving cost strategy, not spreadsheet jockeys in finance. Caleb holds a degree from Georgia Tech and made an unconventional journey into tech from a background in carpentry, which may explain his preference for building things over just talking about them. He's based in Atlanta.

Links:

LinkedIn: https://www.linkedin.com/in/calebrhurd/

Sponsored by:
duckbillhq.com

In this episode, Corey Quinn sits down with Dexter Horthy, CEO and Co-founder of Human Layer, to unpack what engineers are getting wrong about AI, especially when it comes to coding agents.

From the obsession with “just throwing more tokens at the problem” to the reality of building scalable AI workflows, Dexter shares hard-earned insights on how to actually push models to their limits. They dive into the evolution of developer workflows, the rise of AI-powered software factories, and why understanding context and verification matters more than raw model power.

If you’re building with AI or trying to, this episode will challenge how you think about what these systems can (and can’t) do.

Show highlights: 

(00:00)Throwing Tokens Too Far

(01:04) Meet Dexter Horthy

(01:52) Personal AI Benchmarks

(04:12) Human Layer Race Condition

(05:59) Rewrites and Tech Debt

(07:19) Software Factories Mindset

(10:20) Verifiable Problems and Token Limits

(13:45) Agents in the Trenches

(18:05) GitHub at Agent Scale

(26:23) Safety Ethics and Closing Thoughts

About Dexter: 

Dexter Horthy is the CEO and Co-Founder of HumanLayer, where he helps engineering teams tackle complex problems in large codebases using coding agents. Previously, he worked in DevOps, SRE, and Solutions Engineering at Replicated, and contributed to lunar navigation software at NASA JPL. Outside of work, he’s a fan of tacos and burpees, though not necessarily in that order.

Links: 

LinkedIn: https://www.linkedin.com/in/dexterihorthy/

Website: https://humanlayer.dev

Sponsored by:
duckbillhq.com

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