Cristian Guillen·May 5When LLMs Start Testing Themselves: Rethinking QA in the Age of AIThere’s something strangely familiar about testing LLMs — until suddenly, it isn’t.
Cristian Guillen·Jan 16What Are Agents, Supervisors, and Models?Over the past months, I’ve had the opportunity to observe — across different enterprise contexts — how the introduction of agents into…
Cristian Guillen·Jun 26, 2025Rethinking How We Teach Programming in the Age of Generative AIFor a while now, I’ve been thinking about how we need to reshape the way we teach programming to adapt to the new techniques unlocked by…
Cristian Guillen·Jan 28, 2025Revisiting Chatbots in 2025: Using RAG in Watson OrchestrateBack in 2018, we had to create a chatbot for a bank capable of answering some basic questions for its customers, like branch hours…
Cristian Guillen·Jan 21, 2025Proactive Incident Resolution: SRE Involvement in the Software Development Process?I had to explain the Site Reliability Engineer(SRE) key concepts like metrics, traces, logs, and the foundational strategies of…
Cristian Guillen·Jan 14, 2025Integration of Generative Models in Academic ProcessesLast year, I had the opportunity to teach a course to a group of third-year university students focused on creating commercial…
Cristian Guillen·Apr 29, 2021Puppeter and Lighthouse testingThe following example use https://pptr.dev/ a Node.js framework for browser automation and https://github.com/GoogleChrome/lighthouse a…