The AWS Developers Podcast

Tipu Qureshi, Senior Principal Engineer at AWS who builds the DevOps Agent and Agent Core, explains agentic AI for operations and release management. He covers autonomous incident investigation and proactive scheduled checks. He demos IDE integration with Kiro and Claude, sandboxed readiness reviews for pipelines, multi-cloud and A2A workflows, and transparent journals capturing every action.

Davide de Sio built KiroGraph as a personal side project to stop his AI agent from burning through credits just searching files. It turned into a community-driven, open-source MCP server that gives Kiro (and other AI agents) a semantic map of your codebase — reducing token usage by up to 80%. We dive into the architecture, security, and modules, how everything runs 100% locally, and how the AWS Community shaped the project's roadmap. Key takeaways: • Code graphs vs. grep — Tree-sitter and AST-based graph generation give AI agents a smarter navigation model, eliminating wasteful file searches. • Architecture module — Detects patterns and prevents drift by validating your codebase against its own structural rules. • Security module — Finds exposed secrets and vulnerabilities by tracing the call graph, born from an AWS Summit Milano talk. • Watchman module — Auto-generates Kiro skills from repetitive patterns, building persistent memory for your agent. • 100% local execution — Embeddings run with Nomic and summarization with Gemma 3, no data leaves your machine. • Spec-driven development — Davide built KiroGraph with Kiro itself, using specs to drive the entire development lifecycle. • Portability — Commit the graph to Git and share it across machines and team members. • Community-driven roadmap — CI/CD integration, validation hooks, and container deployment are next.With Davide de Sio, Head of Software Engineering at ElevaKiroGraph — Open-Source Code Knowledge Graph (GitHub)Kiro IDE — AI-Powered Development EnvironmentTree-sitter — Incremental Parsing SystemNomic Embed — Local Text EmbeddingsAWS Community Builders ProgramDavide's Blog — Building KiroGraphKiroGraph-Sec — From AWS Summit Milano to a Cybersecurity Feature

Warren Parad, CTO at Authress and host of Adventures in DevOps, brings a contrarian, practitioner-focused view on LLMs and developer workflows. He talks about AI as a multiplier that can amplify broken processes. He warns about agent opacity, approval fatigue, and scope creep. He favors spec-driven development, targeted LLM use for refactors, and governance-first approaches for real impact.

James Price-Farr, AI Engineering Team Lead at Xelix (builds production ML and agentic systems), and Paul Solomon, Head of AI Engineering at Xelix (scales AI/ML for enterprise accounts payable). They explain why evaluating tool calls beats just checking outputs. They cover three automation tiers, steering files vs prompts, orchestration pitfalls, Bedrock rollout lessons, and scaling automation from 10% up.

Ryan Cormack, Principal Engineer at Motorway and AWS Community Builder, shares how he scaled AI coding agents across 120+ engineers. He breaks down five quality gates that enabled 250% more deployments. Short, punchy takes cover spec-driven planning, AI-assisted reviews, deterministic tests, complexity checks, parallel agents, and tooling for wide adoption.

Christian Weichel, CTO and co-founder of Ona and developer tooling expert, explains how cloud dev environments enable autonomous background agents that write code, open PRs, and ship fixes. He outlines three AI stages in the SDLC, why review becomes the new bottleneck, and how risk-based governance, multi-agent review, and isolated environments keep agent-driven workflows safe.

Lewis James, Senior Data Scientist at Reach PLC who built the Launchpad generative-AI publishing platform. He recounts scaling a GPT proof-of-concept to hundreds of thousands of AI-assisted articles. Conversations cover building journalist trust, multi-model pipelines and quotation checks, agentic workflows on Bedrock AgentCore, and the new “vibe publishing” chatbot for creative control.

Tomasz Ptak, Senior Engineer at Duco and AWS AI Hero known for AI-native data automation and community programs, shares lively takes on AI-driven developer workflows. He explores how AI can amplify existing friction, the value of gamified learning like the AWS AI League, and why psychological safety, systems thinking, and rethinking processes matter as teams adopt AI.

Matheus Guimaraes, Senior Developer Advocate at AWS with 25+ years in distributed systems, explores agentic AI reshaping architectures. He contrasts deliberate monoliths and modular designs. He explains agentic microservices, context dilution, serverless runtimes for agents, and how AI coding assistants shift architects toward higher-order decisions.

CyberArk's support team was drowning in logs. With 40+ products across SaaS and self-hosted environments, each generating logs in different formats, support engineers were spending days just preparing data before they could even start investigating a customer issue. Complex cases took up to 15 days to resolve. Moshiko Ben Abu, a Software Engineer at CyberArk — now part of Palo Alto Networks — built an AI-powered system that changed all of that. In this episode, he walks us through the full architecture: replacing manual regex parsers with AI-generated grok patterns using Amazon Bedrock and Claude, storing structured data in Apache Iceberg tables via PyIceberg with automatic schema evolution, and querying everything through Athena — all while keeping PII masked and data encrypted in S3. But the real breakthrough came with agents. Moshiko describes how he moved from single-product Bedrock agents to a swarm of specialized AI agents built with the Strands framework, where agents investigating product A can autonomously call agents for product B and C to trace root causes across the entire stack. Cases that took 15 days now resolve in hours. Simple cases drop from 4-6 hours to 15-30 minutes. Engineers handle 4x more cases per day. We also dig into the security layer — Cedar policies and Amazon Verified Permissions for agent authorization, the identity integration with AgentCore, and what's coming next: S3 Tables, AgentCore in production, and cross-platform agent collaboration with Palo Alto. Moshiko's advice for developers getting started? Learn IAM first, then compute, then databases — and write everything in CDK.With Moshiko Ben Abu, Software Engineer, CyberArk (a Palo Alto Networks company)How CyberArk Uses Apache Iceberg and Amazon Bedrock to Deliver up to 4x Support Productivity — AWS BlogApache Iceberg on AWSPyIceberg — Apache Iceberg Python LibraryAmazon Bedrock AgentCoreStrands Agents — Open-Source Agentic FrameworkCedar Policy LanguageAmazon Verified PermissionsAmazon S3 TablesKiro — AI-Powered Development EnvironmentAWS CDK (Cloud Development Kit)Ran the Builder — Ran Isenberg's Serverless BlogRan Isenberg — AWS Serverless Hero