The Renaissance Developer - Dr. Werner at AWS re:Invent 2025
Dr. Werner Vogels delivered his final AWS re:Invent keynote in 2025, announcing his departure from the platform for new speakers. He assured developers that those who continue to evolve will not become obsolete despite AI transforming tasks. Vogels introduced a five-part framework for the modern "Renaissance Developer," highlighting curiosity, systems thinking, and polymathic knowledge. He stressed the need for precise communication given generative AI's ambiguity. Guest Claire Liguori supported this by detailing spec-driven development (SDD) in the Kiro IDE to manage natural language prompts. Vogels concluded by emphasizing that developers retain sole responsibility for software quality, requiring stronger verification mechanisms like rigorous code reviews for AI-generated work.
--------
12:28
--------
12:28
The RPI workflow (Research, Plan, Implement) - for advanced AI Coding Agent
Dive into the world of Advanced Context Engineering, tackling the challenges of AI-generated "slop" and high rework rates often found when using coding agents on complex or brownfield codebases. We explore the methodology of frequent intentional compaction, utilizing the "Research, Plan, Implement" workflow to manage context windows and maximize LLM output quality. Learn how this plan-first approach enables engineering teams to maintain mental alignment and reliably ship complex, production-ready code while staying out of the "dumb zone".
--------
14:01
--------
14:01
The complete IDE workflow for AI-driven development - the BMAD method
Welcome to the ultimate BMAD Method masterclass, demonstrating the complete IDE workflow for AI-driven development using Claude Code. This episode walks you through transforming a simple to-do application idea, starting with brainstorming with agents like the Analyst, and moving through the creation of necessary artifacts (PRD, Architecture). Learn how to leverage the full suite of agents, including the Analyst and Product Manager, and utilize techniques like advanced elicitation and document sharding to streamline development entirely within your IDE.
--------
12:05
--------
12:05
Weaponizing AI: The Rise of Autonomous Cyber Attacks
Autonomous AI agents execute hyper-personalized phishing and polymorphic malware attacks at unprecedented speed and scale. This acceleration creates a critical "Attack Tempo Gap" that traditional human-centric defenses cannot bridge, posing an existential threat to critical infrastructure. Organizations must deploy AI-driven countermeasures, including Zero Trust and Generative Adversarial Networks (GANs), to match machine-speed offense with machine-speed response.
--------
45:41
--------
45:41
MAKER: Million-Step LLM Tasks with Zero Errors
Large Language Models typically fail long-horizon tasks due to persistent error rates, often derailing after only a few hundred steps. This episode explores MAKER, the first system to successfully solve a task requiring over one million LLM steps with zero errors. Discover how Massively Decomposed Agentic Processes (MDAPs) utilize extreme decomposition into focused microagents and efficient error-correcting voting to provide a reliable, scalable paradigm for future AI systems.
> Building the future of products with AI-powered innovation. <
Build Wiz AI Show is your go-to podcast for transforming the latest and most interesting papers, articles, and blogs about AI into an easy-to-digest audio format. Using NotebookLM, we break down complex ideas into engaging discussions, making AI knowledge more accessible. Have a resource you’d love to hear in podcast form? Send us the link, and we might feature it in an upcoming episode! 🚀🎙️
México