Generative AI

Introduction Most generative AI demos work. Most generative AI systems fail. That gap isn’t about model quality—it’s about system design. Over the past year, I’ve been experimenting with applying large language models to real engineering workflows—generating structured outputs from messy inputs, integrating enterprise data, and building agent-like systems. The biggest lesson so far: prompting is the easy part. Building something reliable around it is the real engineering problem. This mirrors a pattern seen in distributed and mobile systems—reliability emerges from architecture, not individual components. ...

Introduction About five years ago, I came across a research paper on Search-Based Software Testing (SBST) published on IEEE. The idea was fascinating: instead of writing test cases manually, software testing could be treated as an optimization problem. Algorithms could explore the space of possible inputs and automatically discover test cases that maximize coverage and expose hidden defects. Conceptually, it felt like a glimpse into the future of testing. But there was a problem. ...