The AWS Developers Podcast

By Amazon Web ServicesTechnology

The AWS Developers Podcast episodes

September 30Is AWS Lambda still serverless?
Is AWS Lambda still serverless? With Managed Instances, MicroVMs, and Durable Functions, Lambda can now run workloads it was never designed for. AWS Serverless Hero Yan Cui explains what changed, what you give up, and why the core serverless promise still holds.
Romain sits down with Yan Cui, AWS Serverless Hero and independent consultant, to discuss how Lambda grew into general-purpose compute and where it fits for AI agents.
Key topics covered: • Why pay-per-use is no longer the whole story, and why that's fine • Lambda vs Fargate vs ECS: packaging a container image is not running a container • Lambda Managed Instances, the 90-minute timeout, and Durable Functions for jobs that run up to a year • Cold starts: why they were never as big a problem as the conversation around them • Lambda MicroVMs as a second sandbox for AI agents and CI/CD runners • AgentCore Runtime vs Lambda MicroVMs for agentic workloads • Observability for event-driven architectures, and what Lambda still gets wrong • Yan's rule: every box on your architecture diagram needs a reason to exist
Chapters: 00:00 Highlights 00:55 Meet Yan Cui, AWS Serverless Hero 05:23 Is Lambda still serverless? 14:36 Lambda vs Fargate vs ECS: where to draw the line 20:46 Lambda Managed Instances explained 24:10 Are cold starts finally dead? 29:45 Lambda MicroVMs, AI agents and S3 Files 37:51 AgentCore Runtime vs Lambda MicroVMs 45:28 What serverless still gets wrong, and observability 56:07 Yan's advice, book pick and AI security worries
With Yan Cui, AWS Serverless Hero and independent consultant
AWS Lambda Managed Instances
AWS Lambda adds 90-minute function timeout for Managed Instances
AWS Lambda MicroVMs
Lambda Durable Functions documentation
Lambda SnapStart documentation
Amazon S3 Files with Lambda documentation
Agent Toolkit for AWS
Amazon Bedrock AgentCore Runtime documentation
Strands Agents
Eric Johnson's cloud development environment on MicroVMs and S3 Files
Honeycomb
The Software Architect Elevator by Gregor Hohpe
Episode 198: Evolving Lambda with Michael Gasch
Production-Ready Serverless workshop by Yan Cui
Yan Cui's blog
Work with Yan Cui
Yan Cui on LinkedIn
1 hr 13 min
September 23Jev: is it just a smarter if-statement?
Is Jev just a smarter if-statement? That's the question everyone's asking about TypeSafe AI's new "System One" model. In this episode, we dig into what Jev actually is: a model that makes fast, typed decisions your code can use directly — and why it points to a bigger shift: stop defaulting to one giant LLM for everything.
Romain sits down with Mike Chambers, Senior Developer Advocate for Generative AI at AWS, to discuss Jev, decision models, and how they complement the LLMs we already know.
Key topics covered: • What Jev is, and why it is not just another LLM • The three primitives: Noul, Choice, and Score • Putting gated decision points inside an agent with Strands • Fast model routing, and why cost and speed are the real win • Why the right tool for the right job is back
Chapters: 00:53 Welcome, and what is exciting in the Bay Area 04:13 What is Jev? 05:24 Why it is not just another model 09:53 A decision model: moving logic back into code 17:31 System One, and Thinking Fast and Slow 19:02 The three primitives: Noul, Choice, Score 22:29 Accessing Jev: API, OpenRouter, SDKs 26:22 Use cases: gated decision points in agents 35:19 Model routing, cost and speed 40:17 Can Jev drive a DeepRacer, and other models to consider
With Mike Chambers, Senior Developer Advocate for Generative AI at AWS
Jev by TypeSafe AI
Sunil Mallya — The Control Loop Is Moving Back Into Code
Strands Agents SDK
Strands Agents Harness SDK
Mistral OCR
Hugging Face Reachy Mini
Hugging Face Microduck
50 min
September 16Building Software Will Never Be The Same
Most developers say AI makes them more productive. Most companies say their teams aren't shipping faster. What's going on?
In this special solo episode, Romain unpacks the data behind the "acceleration whiplash," walks through a four-level AI maturity framework built from hundreds of customer conversations, and shares the practical lessons that separate teams getting incremental gains from those achieving 10x outcomes. This is a recording of his AI-DLC presentation, delivered at the AWS Summit in Zurich and iterated based on feedback from startups, enterprises, and digital-native companies across Europe.
Key topics covered: • The adoption paradox: individual productivity up, team delivery flat • Why vibe coding is a mirage for production systems • Theory of constraints applied to AI-era software development • The four-level AI maturity framework: Traditional, AI-Assisted, AI-Augmented, and AI-Native • From prompt engineering to context engineering to loop engineering • Cross-functional teams and the evolution of Amazon's two-pizza teams • AI-DLC workshops: mob elaboration, construction bolts, and continuous delivery • Building AI fluency across your organization • The technology stack for AI-native development • Werner Vogels' Renaissance Developer and T-shaped engineers
Chapters: 00:00 Introduction and why this episode exists 01:28 The evolution of coding assistants (2004–2026) 05:01 Systems of agents and software factories 06:27 The adoption paradox: faster developers, slower teams 09:05 Vibe coding is a mirage 10:12 Theory of constraints and The Phoenix Project 12:17 You can't bolt AI on existing workflows 13:03 Start with why: what are you optimizing for? 15:33 The four-level AI maturity framework 24:30 Level 3 and 4: loop engineering and frontier teams 26:57 People, process, and technology transformation 37:56 The AI-DLC technology stack 41:09 Mindset: the Renaissance Developer 43:24 Practical lessons learned at every level
Faros AI Engineering Report 2026 — The Acceleration Whiplash
Amazon's Cost-to-Serve Software Metric
Amazon Science — Measuring Software Development Effectiveness
Werner Vogels' re:Invent 2025 Keynote — The Renaissance Developer
Boris Cherny on Loop Engineering
Netflix CPTO Elizabeth Stone — Systems Thinkers in the AI Era
Strands Agents — Open-Source Agentic Framework
Kiro — Spec-Driven Development
Amazon Bedrock AgentCore
The Phoenix Project — Gene Kim, Kevin Behr, and George Spafford
Start with Why — Simon Sinek
Team Topologies — Matthew Skelton and Manuel Pais
52 min
September 02Kiro, Strands Agents & MCP: 10 Updates You Missed
The MCP specification just went stateless. Clare Liguori — Senior Principal Engineer at AWS and core MCP maintainer — explains what changed, why it matters, and what it unlocks for agent developers building with Strands Agents and Kiro. In this episode, Romain sits down with Clare Liguori, Senior Principal Engineer at AWS, to discuss the July 28 MCP spec release, new MCP extensions (Skills, Tasks, Events), Strands Agents Harness SDK, Strands Shell, Physical AI in Strands Labs, and the latest Kiro updates across Web, CLI, IDE 1.0, and iOS. Key takeaways: • MCP goes stateless — the July 28 spec release removes the need for stateful streaming in remote MCP servers, so SaaS providers can drop sticky sessions and load-balancer gymnastics and run each request anywhere. Expect a new wave of remote MCP servers over HTTP. • New MCP extensions framework — features now start as stable extensions before graduating into the official spec: Skills over MCP (bundle a workflow and its tools together), long-running Tasks (kick off builds or jobs without blocking the agent), and Events (trigger always-on agents from external signals like Slack or an earthquake feed). • Strands Agents Harness SDK & TypeScript 1.0 — a more batteries-included harness with context management, compaction, and excellent out-of-the-box file tools, plus the TypeScript SDK reaching 1.0. Upgrade the model ID and your agent gets better. • Strands Shell — a lightweight, in-process agent sandbox written in Rust (cross-platform, Python SDK today). It gives an agent a virtual file system and minimal bash/Lua scripting without a heavyweight VM — great as a safe scratch pad or for scripting tools together. • Strands Labs & Physical AI — an experimental space for bleeding-edge agent ideas, including combining low-latency local VLA models on robots with the long-range, multi-task reasoning of frontier models in the cloud. • AgentCore Managed Harness — a configuration-based way to run agents (prompt, model, Lambda tools, context and session management) that is Strands under the hood, no Python or TypeScript required. AgentCore Gateway added MCP 2026-07-28 support day one, with version negotiation for backward compatibility. • One unified Kiro harness — Kiro Web, iOS, CLI, and IDE 1.0 now share one harness, bringing spec-driven development, hooks, skills, and powers to every client and letting new features ship across clients on the same day. • Automated reasoning in specs — property-based testing plus ambiguity and conflict detection in requirements help you express intent clearly; the permission system is built on Cedar with policy presets like dev shell, trust all, and read all. • Right-sizing specs and collaborating — check specs into code as a snapshot of intent, watch design and task-list length as a signal to split into multiple specs, add per-task validation steps, and collaborate on specs with comments in Kiro Web.
With Clare Liguori, Senior Principal Engineer at AWS
MCP Specification (2026-07-28)
Strands Agents SDK on GitHub
Strands Agents Harness SDK
Strands Shell
Strands Agents TypeScript SDK
Kiro — AI-Powered Development Environment
Amazon Bedrock AgentCore Gateway
How AgentCore Gateway supports the MCP 2026-07-28 spec
Lean language
Cedar — Permission Language
Custodians of Wonder — Eliot Stein (Clare's Book Recommendation)
Clare Liguori on LinkedIn
1 hr 3 min
August 26Harness engineering: are you controlling your AI agents?
What happens when you strip the model from an agent? Everything left is the harness — and engineering that harness is the new discipline every AI builder needs to master. In this episode, Romain sits down with Mike Chambers, Senior Developer Advocate for Generative AI at AWS, fresh from speaking at the AI Engineers World's Fair 2026. They dig into harness engineering — what it means, why it matters, and how it changes whether you're building or using agents. Mike introduces “slop ops” (his term for unconstrained agent deployments), explains the difference between Strands Agents SDK and AgentCore Harness, and shares why small language models are his next big bet. Key takeaways: • Harness engineering is the discipline around everything left when you remove the model from an agent — including tools, skills, memory, context, observability, evaluations, and the agentic loop • The agent you use and the agent you build require different harness thinking — personal coding agents can optimize for productivity, while production agents must manage context, cost, scale, and reliability • AgentCore Harness removes undifferentiated orchestration code — provide a model, system prompt, tools, and skills through configuration, and the service creates and runs the agentic loop • Avoid “slop ops” — agents should generate infrastructure as code rather than directly creating unconstrained cloud resources, keeping deployments repeatable, reviewable, and owned by the team • Evaluation must evolve alongside an agent — it is difficult to retrofit and cannot be treated as a one-time prerequisite or an afterthought • FOMAT, the fear of missing agent time, can push developers toward unhealthy always-on behavior — faster execution still requires space to think deeply about which problems are worth solving • Kiro for iOS enables mobile-first agentic workflows — Mike uses walks to think, dictate ideas, delegate experiments, and return to working prototypes • Small language models can make focused agentic workloads faster and more cost-effective once teams understand the task well enough to specialize the model
With Mike Chambers, Senior Developer Advocate for Generative AI at AWS
AI Engineers World's Fair 2026
Strands Agents SDK
Strands Agents on GitHub
Strands Agents Harness SDK
Amazon Bedrock AgentCore Harness
Kiro for iOS
Latent Space Podcast
Mike Chambers on Coursera
51 min
July 29
title: “How Prime Video’s engineers manage agents, not code”
description: “Prime Video serves over 300 million monthly customers across 240+ territories and 8,000+ device types. Lilia Abaibourova leads the AI-native transformation there. Prime Video started early, adopting CodeWhisperer as soon as it became available in preview, progressing through Amazon Q Developer, and now using Kiro to put agentic development in the hands of engineers, product managers, and designers.
Romain sits down with Lilia to trace that journey — from CodeWhisperer preview to Amazon Q Developer and now Kiro — and explore MCP as the organizational inflection point: teams run two-person pods with full decision autonomy, while managers oversee fleets of agents instead of just headcount.
Key takeaways:
• Prime Video adopted AI coding tools from day one — CodeWhisperer in preview, then Amazon Q Developer, and now Kiro — building institutional muscle even when specific features were later sunset
• MCP was the inflection point for organizational (not just individual) transformation — connecting disciplines end-to-end and eliminating handoff bottlenecks
• Code generation is now effectively solved; the new frontier is verification, validation, and code review at scale
• Team structures are being actively experimented with — from 2-person pods with full autonomy to larger teams where managers leverage agent fleets
• The biggest anti-pattern: waiting on the sidelines for a standard instead of learning through experimentation”
guests:
name: “Lilia Abaibourova”
link: https://www.linkedin.com/in/abaibourova/
bio: “Principal Product Manager leading AI-native transformation at Prime Video. Started as a developer at Microsoft, later became a software development manager, then moved to HBO to build large-scale streaming infrastructure on AWS. For the past two years has led Prime Video’s AI enablement program spanning tooling, MCP infrastructure, and organizational experimentation. Based in Seattle.”
title: “Principal Product Manager, AI-Native Transformation at Prime Video”
episode: 219
duration: “01:11:24”
size: 0
file: 219.mp3
social-background: 219.png
publication: 2026-07-29 09:00:00 +0200
author: “Romain Jourdan”
category: podcasts
aws-categories:
“Machine Learning & AI”
“Developer Tools”
“Management & Governance”
links:
text: “Lilia Abaibourova at AWS re:Invent 2025”
link: https://youtu.be/hyyb4-0KVaw
text: “Prime Video”
link: https://www.primevideo.com/
text: “Kiro — AI-Powered Development Environment”
link: https://kiro.dev/
text: “Amazon Bedrock AgentCore”
link: https://aws.amazon.com/bedrock/agentcore/
text: “Strands Agents SDK — Open Source”
link: https://github.com/strands-agents/sdk-python
text: “Introducing the Model Context Protocol (Anthropic)”
link: https://www.anthropic.com/news/model-context-protocol
text: “A Return to Two-Pizza Culture — Werner Vogels”
link: https://www.allthingsdistributed.com/2026/06/return-to-two-pizza-culture.html
text: “I, Robot — Isaac Asimov (Lilia’s Book Recommendation)”
link: https://www.amazon.com/Robot-Isaac-Asimov/dp/0553294385
text: “Lilia Abaibourova on LinkedIn”
link: https://www.linkedin.com/in/abaibourova/
0 min
July 29How Prime Video's engineers manage agents, not code
Prime Video serves over 300 million monthly customers across 240+ territories and 8,000+ device types. Lilia Abaibourova leads the AI-native transformation there. Prime Video started early, adopting CodeWhisperer as soon as it became available in preview, progressing through Amazon Q Developer, and now using Kiro to put agentic development in the hands of engineers, product managers, and designers. Romain sits down with Lilia to trace that journey — from CodeWhisperer preview to Amazon Q Developer and now Kiro — and explore MCP as the organizational inflection point: teams run two-person pods with full decision autonomy, while managers oversee fleets of agents instead of just headcount. Key takeaways: • Prime Video adopted AI coding tools from day one — CodeWhisperer in preview, then Amazon Q Developer, and now Kiro — building institutional muscle even when specific features were later sunset • MCP was the inflection point for organizational (not just individual) transformation — connecting disciplines end-to-end and eliminating handoff bottlenecks • Code generation is now effectively solved; the new frontier is verification, validation, and code review at scale • Team structures are being actively experimented with — from 2-person pods with full autonomy to larger teams where managers leverage agent fleets • The biggest anti-pattern: waiting on the sidelines for a standard instead of learning through experimentation
With Lilia Abaibourova, Principal Product Manager, AI-Native Transformation at Prime Video
Lilia Abaibourova at AWS re:Invent 2025
Prime Video
Kiro — AI-Powered Development Environment
Amazon Bedrock AgentCore
Strands Agents SDK — Open Source
Introducing the Model Context Protocol (Anthropic)
A Return to Two-Pizza Culture — Werner Vogels
I, Robot — Isaac Asimov (Lilia's Book Recommendation)
Lilia Abaibourova on LinkedIn
1 hr 12 min
July 22Your AI platform isn't mature — here's what is
I keep hearing 'we're building an AI platform' from enterprises. Most are stitching together demos. Thomson Reuters has been doing AI for 30 years. I sat down with Laura Skylaki (VP AI Engineering, Thomson Reuters) at AWS Summit London — and the gap between what they're doing vs. what most companies call 'AI maturity' is striking. In this episode, Laura breaks down how Thomson Reuters built an enterprise AI platform that serves 30,000 employees across three user personas — from business users to AI creators to developers — with 16 internal services, a $200M/year AI commitment, and a healthy skepticism about when agentic is actually the right answer. Key takeaways: • Evaluation before building — 'It's increasingly harder to retrofit an evaluation framework to an agent capability you already deployed.' They build evaluation benchmarks first to force understanding of the business problem, then build the agent. LLM-as-a-judge with human-in-the-loop calibration — and the judges themselves need continuous regression checks. • Know when NOT to use agents — 'Where we can go and write deterministic code with a logical rule-based approach, I don't think it makes sense to rely on the agent.' Not everything needs to be agentic. When tools exceed a dozen or overlap semantically, specialize into multiple agents instead of overloading one. • Engineers haven't written code manually in 3-4 months — Not experimenting; their AI coding tooling is that far ahead. The shift is toward system design, architecture, and clear structuring for AI assistance. • AWS under the hood with AgentCore and Strands — The platform runs on AWS with API Gateway, Lambda, Step Functions, and Amazon Bedrock AgentCore for agent deployments (runtime, memory, MCP marketplace, code interpreter, browser tools, policy and identity governance). They use Strands Agents SDK to build agents. AgentCore removes the infrastructure burden of long-running agent sessions. • Rethink workflows, don't retrofit — Teams reimagining legacy workflows from scratch for AI rather than bolting generative AI onto systems not built for it. 'If I was building this now for the first time, how would I build it?' The companies that succeed with AI are not fitting it into existing processes — they're redesigning the process through AI.
With Laura Skylaki, VP of AI Engineering at Thomson Reuters
Thomson Reuters — AI & Technology
CoCounsel — AI Assistant for Legal Professionals
Amazon Bedrock AgentCore
Strands Agents SDK
AWS Summit London 2026
Automated Reasoning on AWS
Extreme Ownership — Jocko Willink & Leif Babin (Laura's Book Recommendation)
Laura Skylaki on LinkedIn
54 min
July 15The Delivery Gap: Why 96% of Your AI Code Is Waste
Brenn reached out via LinkedIn to share his experience with AI-driven software development and his new book, The Delivery Gap. Romain read a copy during a business trip and found it deeply aligned with how he guides customers through their AI transformation — and discovered a few new angles worth exploring, including a convergence on cost tracking that maps directly to Amazon's internal cost to serve software metric. In this episode, Brenn — Senior Manager at Delivery Hero (one of the world's largest food delivery companies, operating in 65 countries) — breaks down why most companies fail to see returns from AI coding tools despite individual developers feeling more productive. The core insight: generating code 10x faster means nothing if your verification infrastructure can't keep up. You're just driving 10x faster into a wall. Key takeaways: • The 96% waste problem — If you generate 100 PRs and only 4 make it to production and stay there, the other 96 are waste. Measuring PRs created is meaningless; measure what ships and survives. • The verification triangle — Your delivery speed is governed by verification infrastructure, not generation speed. Banks can't release faster than they can audit. Find your constraint — that's where investment should go, not more coding tools. • Cost per accepted change — Total token costs + human time for all PRs, divided by changes that reach production and stay there. This single metric reveals where waste accumulates and aligns with Amazon's cost to serve software model. • Specs as alignment documents, not source code — Specs align humans and AI on intent and why, not for deterministic code generation. The same spec produces different software each time. Focus on why; let the AI document the what. • Keep agents small and focused — Every MCP server re-injected into context is a cost multiplier per turn. The smallest, tightest, most precisely aimed agent outperforms a Swiss Army knife agent on both cost and accuracy. Apply cost per accepted action to measure agentic ROI.
With Brenn, Senior Manager at Delivery Hero & Author of The Delivery Gap
The Delivery Gap — Brenn's Book
Business Value of Developer Experience Improvements: Amazon's 15.9% Breakthrough
Delivery Hero — Global Food Delivery Platform
AWS DevOps Agent
Kiro — AI-Powered Development Environment
The Phoenix Project — Gene Kim, Kevin Behr, George Spafford (Book Recommendation)
The DevOps Handbook — Gene Kim, Jez Humble, Patrick Debois, John Willis (Book Recommendation)
Warp — AI-Powered Terminal (Brenn's Dev Tool Pick)
Brenn on LinkedIn
Episode 214 — AWS DevOps Agent: Can Your Pipeline Keep Up with AI?
1 hr 8 min
July 08What are MCP apps and why should you care?
Most MCP tools today return text. But what if your agent could render a chart, a form, or a full dashboard right inside the chat? That's what MCP apps do — and they're already live on ChatGPT, Claude, and Amazon Quick. Romain sits down with Luigi Pederzani, co-founder of Manufact (the company behind mcp-use, 10K+ GitHub stars), to explore MCP apps — the first official extension of the MCP protocol that lets servers return interactive UI inside AI chat interfaces. Key takeaways: • What MCP apps are — Standard MCP returns text and actions; MCP apps let a server send back a piece of interface (a form, a chart, a dashboard) that renders right inside the chat. It became the first official extension of the protocol this year, growing out of MCP-UI. • UI drives retention — Amplitude saw 2x retention for users exposed to a chart-rendering MCP app versus text-only responses. UI lets software products stay experiences, not just systems of record. • AI apps are the new browsers — Extending Paul Graham's thesis, every software product will be rendered inside AI chats, pulling data and structure from different sources the way we switch tabs today. • Building with mcp-use — Reuse existing React components with minimal changes; the useMcp hook bridges tool arguments (filled by the agent) into component props. The server stays a normal MCP server, the client is the host, and the view runs in a sandboxed iframe. • Interactivity and safety — Iframes are battle-tested and the model-to-server communication is standardized. UI can send events back to the model, so clicking a chart element can trigger another tool call in the chat. OAuth is now standard for production MCP servers. • Tool design best practices — Don't wrap OpenAPI specs directly as MCP. APIs are granular and atomic; MCP tools should serve a task end-to-end so agents don't get confused on ordering. Limit the number of tools exposed; progressive disclosure is now handled by the major clients. • MCP as the A2A protocol — A2A never really landed, and MCP is becoming the agent-to-agent protocol, with companies embedding an agent as a single tool whose main argument is a prompt. • Getting to production — Start with a plain MCP server, then add UI. Skills are now part of the product, and Manufact focuses on agent-readiness of the SDK, testing across clients, deployment, auth, observability (OTEL), and per-tool analytics. • AWS integration — mcp-use can sit on the server side while AgentCore Gateway sits in front to handle enterprise concerns like auth policies and routing. • What's next — Exposing skills directly from MCP servers (rather than decoupled files), and the next stateless-by-default release of the protocol.
With Luigi Pederzani, Co-founder of Manufact
mcp-use SDK (GitHub)
Manufact Cloud
Ora.ai — Agent Readiness Scanner
Amazon Bedrock AgentCore Gateway — MCP Server Targets
AgentMail — Email Infrastructure for Agents
Thinking, Fast and Slow — Daniel Kahneman (Luigi's Book Pick)
Luigi Pederzani on LinkedIn
51 min