Agentic AI
Autonomous agents, tool use, evaluation, and the emerging LLM stack.
What are MCP apps and why should you care?
Luigi Pederzani, co-founder of Manufact (behind mcp-use), on MCP apps - the first official extension of the MCP protocol that lets servers return interactive UI inside AI chat interfaces like ChatGPT, Claude, and Amazon Quick.
5 Lessons Running AI Agents in Production
John Sexton and Aaron Tummon of Genesys share five hard-won lessons from running an agentic AI copilot for 2 million users across 21+ AWS regions - framework choice, orchestration, context management, prompt caching, and relentless testing.
AWS DevOps Agent: Can Your Pipeline Keep Up with AI?
Tipu Qureshi on how the AWS DevOps Agent autonomously investigates incidents, validates code changes in sandboxes, and manages releases across clouds - with IDE integration through Kiro and Claude.
KiroGraph: How a Local Code Graph Saves 80% of Your AI Tokens
Davide de Sio on KiroGraph, an open-source, fully local MCP server that gives AI agents a semantic map of your codebase and cuts token usage by up to 80%.
Cutting Through the AI Developer Hype
An honest, no-filter conversation with Warren Parad on where developers really stand with AI - why 93% feel productive but only 4% of enterprises see results, and what separates those who benefit from those who don't.
Why Your Agent Evaluations Will Fail You (and How to Fix Them Before Production)
Recorded live at AWS Summit London, Paul Solomon and James Price Farr of Xelix share an evaluation-first framework for keeping agentic systems stable through model migrations, orchestration changes, and tool-selection errors.
Dark Factories: Why Your AI Coding Setup Is Already Outdated
Christian Weichel, CTO of Ona (formerly Gitpod), on 'dark factories' - autonomous background agents that pick up work, write code, and open PRs while you sleep - and the governance model that makes them safe for regulated enterprises.
LLM-as-a-Judge, Quotation Fidelity, and A/B Testing Models: AI Publishing at Scale
Recorded live at AWS Summit London, Lewis James of Reach PLC on scaling a production generative AI publishing platform to 700,000 articles with multi-model pipelines, quotation-fidelity checks, and agentic workflows on Amazon Bedrock AgentCore.
AI Agents, Friction, and the Future of Developer Experience
Recorded live at AWS Summit London, AWS AI Hero Tomasz Ptak on developer experience friction in the age of AI agents, and why critical thinking about AI adoption matters more than blind acceleration.
How Can AI Agents Cut Support Resolution Time by 95%?
Moshiko Ben Abu of CyberArk on building a swarm of specialized AI agents with Strands, Amazon Bedrock, and Apache Iceberg that cut complex support cases from 15 days to hours.
Neurosymbolic AI: Combining GenAI with Mathematical Proof - with Danilo Poccia
Danilo Poccia on automated reasoning and neurosymbolic AI - combining generative AI with formal verification, and using Amazon Bedrock Guardrails with Automated Reasoning checks for reliable agents.
Agent-Native Serverless Development with Shridhar Pandey
Shridhar Pandey on how the AWS Serverless team is pioneering agent-native development with Kiro Powers, an agent plugin for Claude Code and Cursor, and an 'agent experience' lens on every feature.
Spring AI and AgentCore: Building Enterprise AI Agents in Java
Episode 200: James Ward and Josh Long on why Java and Spring AI are becoming the go-to stack for enterprise AI agents, plus Agent Skills, the Java MCP SDK, and Amazon Bedrock AgentCore.
AWS Hero Linda Mohamed: Juggling Cloud, Community & Agentic AI
AWS Community Hero Linda Mohamed on her journey from Java developer to building multi-agent AI systems with Crew AI and Amazon Bedrock AgentCore, and an AI-powered video pipeline.
Your AI Agent Can't Multitask - Here's How to Fix It
Mike Chambers returns to unpack OpenClaw, asynchronous tool calling built on the Strands Agents SDK, and whether embedding generative capability in code is 'Software 3.1'.
Chris Miller on AI Coding, Multi-Agent Systems, and the Silicon Valley Vibe
AWS Hero Chris Miller on multi-agent architectures, moving beyond vibe coding to responsible AI development, and what it's really like building in Silicon Valley's AI boom.
From MCP to Multi-Agents: The Evolution of Agentic AI (and What's Next)
Mike Chambers reflects on 2025 as 'the year of agents' - from MCP's rocky launch to the rise of AI coding assistants and lightweight frameworks like Strands, ADK, and Spring AI.