Episode 48: Rethinking Software Engineering through a Spec-Driven Approach with Kiro

AI agents aren't just answering questions anymore — they're executing workflows, modifying data, and making autonomous decisions across your most critical systems. As AI agents take on more complex tasks operating at scale and encounter unexpected situations, establishing robust governance and recovery mechanisms becomes increasingly important. Most organizations currently lack the systems needed to manage and address these scenarios effectively.In this episode of the AWS re:Think Podcast, hosts Malini Chatterjee and Jay Sampath sit down with Swami Ramany (GVP, Product Management) and Rob Sadowski (VP, Product & Tech Marketing) from Cohesity to explore the emerging discipline of Agent Resilience — the missing recovery layer for agentic AI at scale. Find further details and demo click HERE Guest: Swami Ramany GVP, Product Management, Cohesity and Rob Sadowski VP, Product & Tech Marketing, CohesityHosts: Malini Chatterjee & Jay Sampath📧 Feedback? [email protected]

Supply chains don't break at the nodes — they break at the seams. Hosts Malini Chatterjee and Diana Conner sit down with Sriram Nagaswamy, EVP of Technology at FourKites, to unpack why a decade of supply chain investment still hasn't solved the handoff problem — and how agentic AI built on Amazon Bedrock is changing the game.From competing on resilience in an era of tariffs and nearshoring, to autonomous agents that act on disruptions (not just report them), this episode covers what it takes to move from visibility to execution at scale.AI agents that autonomously execute supply chain operations — built on the world's first Intelligent Control Tower, powered by 1.1M carriers and suppliers across 200+ countries. For details on how to get started, visit FourKites.aiGuest: Sriram Nagaswamy, EVP of Technology, FourKitesHosts: Malini Chatterjee & Diana Conner📧 Feedback? [email protected]

In Part 2 of our AWS Summits recap, Geries AbouAyash, AWS Managing Director, North America Solutions Architecture joins Malini and Amit to unpack what the shift to agentic AI really means for how we work. From Amazon Quick's autonomous agents ("Quick Just Does It") to Kiro on iOS, DevOps Agent, and Transform — and the infrastructure changes powering the emerging agent economy, like S3 Annotations and AWS WAF AI Traffic Monetization — the conversation goes beyond announcements to the bigger question: does AI just help us do more, or help us do more meaningful work? The throughline: AI isn't about replacing people — it's about removing undifferentiated work so builders, engineers, and leaders can spend more time where they create the greatest value.https://kiro.dev/blog/introducing-kiro-for-ios/https://aws.amazon.com/devops-agent/features/?trk=bdad73ef-9780-48b0-b82e-6d92ad86fcf6&sc_channel=pshttps://aws.amazon.com/about-aws/whats-new/2026/04/aws-transform-kiro-vscode/https://docs.aws.amazon.com/AmazonS3/latest/userguide/annotations-overview.htmlhttps://aws.amazon.com/about-aws/whats-new/2026/06/aws-waf-ai-traffic-monetization/AWS Hosts: Amit Narayanan & Malini ChatterjeeEmail Your Feedback: [email protected]

Three AWS Summits across the US — LA on June 10, NYC on June 17, and Washington DC on June 30–July 1 — brought a wave of announcements that all orbited a single thesis: the age of agentic AI is here, and the winners will be organizations whose agents get smarter with every decision they make. In this episode, AWS Managing Director, North America Solutions Architecture, Geries AbouAyash joins hosts Malini and Amit to break down four major Summit announcements — Graviton5, AWS Context, AgentCore Harness, and AWS Continuum — spanning next-gen CPUs for agentic workloads, a governed knowledge graph that gives agents organizational memory, production-grade agent deployment, and security at machine speed. The throughline: in the age of Agentic AI, the challenge is no longer building intelligence but operationalizing it — and as foundation models become universally accessible, competitive advantage shifts from who has the model to who can run AI securely, efficiently, and at enterprise scale.https://aws.amazon.com/blogs/aws/top-announcements-of-the-aws-summit-in-new-york-2026/https://www.aboutamazon.com/news/aws/aws-graviton-5-cpu-amazon-ec2https://aws.amazon.com/blogs/machine-learning/context-intelligence-for-your-data-and-ai-agents-at-scale/AWS Hosts: Amit Narayanan & Malini ChatterjeeEmail Your Feedback: [email protected]

Modern cloud environments are evolving faster than traditional security models can keep up. In this episode, we sit down with Yarin Pinyan, VP Products at Upwind, to explore how real-time runtime visibility and behavioral baselining are reshaping how organizations detect and respond to threats, especially zero-day and supply chain attacks that emerge before signatures or CVEs exist. We’ll also discuss how AI is enabling a new generation of cloud security, where detection, investigation, and response happen continuously and automatically. The conversation highlights how organizations can reduce risk, improve operational efficiency, and protect critical workloads in dynamic, cloud-native environments.AWS MP offering: https://aws.amazon.com/marketplace/pp/prodview-ff3am62vjukrw?sr=0-1&ref_=beagle&applicationId=AWSMPContessaWebsite: https://www.upwind.io/Customer success story: https://www.upwind.io/case-studiesAWS Hosts: Nolan Chen & Ashok MahajanEmail Your Feedback: [email protected]

AI agents move at machine speed. Your security doesn't. Discover how enterprises are finding shadow agents, measuring agent ROI, and transforming agentic AI from risk to strategic value. Learn from Arti Arora Raman, CEO Founder of Portal 26 and Neil Cohen, VP of Marketing in Portal 26 how Portal26's platform capabilities mitigate enterprise challenges around AI adoption, security, ROI, and governance. AI agents operate autonomously at machine speed, making decisions and tool calls without human approval. But most enterprises don't know which agents are running, what they're accessing, or whether they're creating value or risk.In this episode of AWS re:Think, host Malini and Preethi explores Portal26's Agent Management Platform (AMP) and how it helps enterprises discover, secure, and measure ROI from agentic AI. We discuss the five primary agentic AI security risks—from rogue agents to agent drift—and how organizations are using agent-level visibility to transform AI from an operational risk into a strategic asset.Learn how finance teams are tracking token consumption, how security teams are identifying high-risk agents before they cause damage, and how enterprises are finally closing the gap between AI investments and returns.Discover how to govern AI agents at the speed they operate.Reference: https://portal26.ai/AWS Hosts: Preethi Ravula & Malini ChatterjeeEmail Your Feedback: [email protected]

In this episode we explore how companies should evaluate AI agents across multiple dimensions — including correctness, tool selection, multi-turn reasoning, and safety . The conversation covers building reliable evaluation frameworks, balancing automated vs. human-in-the-loop testing, and leveraging observability to debug agent behavior in production.Links from the ShowAgentCore Evaluation: https://github.com/awslabs/agentcore-samples/tree/main/01-tutorials/07-AgentCore-evaluationsStrands Evaluation: https://strandsagents.com/docs/user-guide/evals-sdk/quickstart/AWS Hosts: Nolan Chen & Malini ChatterjeeEmail Your Feedback: [email protected]

In this episode we join AWS Senior GTM Specialists Aidin Khosrowshahi and Rakesh Kumar to unpack how Kiro is transforming software development through a spec-driven approach that goes beyond traditional AI-assisted coding. We cover what sets spec-driven development apart from "vibe coding" and why Kiro's spec-first approach matters. We also tackle the mindset shifts developers must make when adopting Kiro. The episode closes with a forward-looking discussion on whether the "Software Engineer" title could eventually be redefined—and the skills and first steps anyone needs to get started with Kiro today.Try Kiro today:kiro.devAWS Hosts: Nolan Chen & Malini ChatterjeeEmail Your Feedback: [email protected]

"Its amazing to see the rate and pace of advancements in technology in 2025" Todd Pond, AWS Director of Strategic Sales, is out in the field with commercial customers every day, helping them leverage technology to solve their biggest problems, accelerate innovation and transform their businesses. He and his team have a deep understanding of these companies - the challenges they're up against, their limited resources, their unique value propositions, and how to enable their growth with maximum ROI. In this episode, we talk to Todd about the learnings from 2025 and get his actionable insights on the biggest opportunities for success in 2026 and beyond. 

Aizon.ai provides an AI software platform for the pharmaceutical and biotech industries to optimize manufacturing processes, ensure GxP compliance, and improve product quality. Their top outcomes include financial savings and improved operational efficiency for clients. Aizon’s ability to optimize manufacturing production and quality in highly regulated industries by providing real-time visibility and predictive insights while ensuring GxP compliance. The AWS case study details how a pharmaceutical company utilized Aizon's AI platform to achieve double-digit yield improvements through clinical process optimization. AWS Hosts: Nolan Chen & Gokhul Srinivasan https://aws.amazon.com/solutions/case-studies/aizon-case-study/https://aws.amazon.com/marketplace/seller-profile?id=5bb4e9b6-8a87-40d9-aea5-adc6ebcad7c0https://www.aizon.ai/success-storiesEmail Your Feedback: [email protected]