Rafa Granados
VP and field CTO at WSO2 |Microsoft MVP| Co-Founder Apicurios Podcast | Apiaddicts
Barcelona, Spain
Actions
Rafael Granados is VP & Field CTO at WSO2, with extensive experience leading API strategies in large organizations. Previously, he led the API strategy within the engineering team at Inditex, where he also drove and released the API Scoring project as open source—a pioneering initiative to improve API quality and governance. Prior to that, he was responsible for founding and consolidating the API strategy at CaixaBank, positioning the bank as one of the leading Open Banking players in Europe.
Rafael is a Microsoft MVP, a regular speaker at international conferences such as API Days Paris and FOSDEM, and shares practical insights on APIs, security, governance, and the impact of AI on modern architectures. He is also the co-founder of “The Apicurios” podcast, a leading Spanish-language resource in the API community, and an active contributor to communities like ApiAddicts.
Area of Expertise
Topics
Mochila de 48h para sobrevivir a la era agéntica
La era agéntica ya está aquí. Los agentes de IA son fundamentales; comprender y gestionar el contexto del modelo es clave. ¿Estás listo para esta realidad?
En esta sesión, abordaremos los básicos y compartiremos estrategias esenciales para sobrevivir en la era agéntica, con un enfoque directo en el rol crítico de las APIs.
Exploraremos cómo las APIs son el motor de la interacción entre agentes y cómo construir sistemas resilientes en entornos definidos por la comunicación Agent-to-Agent (A2A), arquitecturas Generative AI Ready (GAR) y, fundamentalmente, el Model Context Protocol (MCP).
Esta charla te proporcionará el kit fundamental para enfrentar la era agéntica. Te llevarás conocimientos prácticos sobre la implementación de APIs que habilitan agentes, la gestión del contexto con MCP, y cómo asegurar que tus sistemas sean GAR.
Your Agent Has Keys. Which Doors Is It Opening?
Modern AI agents don't just chat — they call real APIs, invoke tools, and execute actions with real-world consequences. That's exactly where most prototypes fall apart. Not because of bad prompts, but because of missing guardrails.
In this session, we'll dissect a production-ready agent built on MCP tools and APIs to answer the uncomfortable question nobody asks until something breaks: who can do what, and how do you prove it?
You'll walk away with:
Your agent follows orders. Make sure it only follows yours
You gave your agent tools. Did you give it limits?
Spy on your own agent before someone else does
The scars of taking an agent to production (and how not to repeat them)
Your agent can open any door. Make sure it only knocks on the right ones.
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top