In this conversation with Malte Ubl, CTO of Vercel, we explore how the company is pioneering the infrastructure for AI-powered development through their comprehensive suite of tools including workflows, AI SDK, and the newly announced agent ecosystem. Malte shares insights into Vercel's philosophy of "dogfooding" - never shipping abstractions they haven't battle-tested themselves - which led to extracting their AI SDK from v0 and building production agents that handle everything from anomaly detection to lead qualification. The discussion dives deep into Vercel's new Workflow Development Kit, which brings durable execution patterns to serverless functions, allowing developers to write code that can pause, resume, and wait indefinitely without cost. Malte explains how this enables complex agent orchestration with human-in-the-loop approvals through simple webhook patterns, making it dramatically easier to build reliable AI applications. We explore Vercel's strategic approach to AI agents, including their DevOps agent that automatically investigates production anomalies by querying observability data and analyzing logs - solving the recall-precision problem that plagues traditional alerting systems. Malte candidly discusses where agents excel today (meeting notes, UI changes, lead qualification) versus where they fall short, emphasizing the importance of finding the "sweet spot" by asking employees what they hate most about their jobs. The conversation also covers Vercel's significant investment in Python support, bringing zero-config deployment to Flask and FastAPI applications, and their vision for security in an AI-coded world where developers "cannot be trusted." Malte shares his perspective on how CTOs must transform their companies for the AI era while staying true to their core competencies, and why maintaining strong IC (individual contributor) career paths is crucial as AI changes the nature of software development. Key Topics: • The Workflow Development Kit and durable execution patterns • Building production agents for DevOps, lead qualification, and data analysis • Why AI SDK stayed low-level while competitors rushed to agent abstractions • The "agent on every desk" program and forward deployment strategy • Zero-config Python support and the future of multi-language platforms • Security models for AI-generated code that assumes developer incompetence • Finding the sweet spot for agent deployment through employee pain points • How Vercel's anomaly detection + agent investigation solves the SRE sleep problem • The importance of dogfooding and extracting abstractions from real usage • Leadership lessons for CTOs navigating the AI transformation