Platforms for Humans and Machines: Engineering for the Age of Agents — Juan Herreros Elorza

Juan Herreros Elorza discusses strategies for optimizing internal developer platforms for AI agents, drawing from his experience at Banking Circle. He argues that while many software development best practices remain crucial, the integration of AI agents amplifies the need for self-service platforms. He advocates for API-based systems to facilitate seamless interaction and discovery for AI agents, emphasizing the importance of shifting processes left for early failure detection. Juan also highlights the need for comprehensive, structured documentation and observability tools accessible via APIs to guide agent behavior and verify task completion. He suggests encouraging contributions to the platform while implementing guardrails for security and compliance, and measuring the impact of these changes using metrics like DORA and SPACE.