This hands-on evaluation examines Google's Jules, an agentic AI that autonomously writes code, runs tests, and creates pull requests. The article explores real-world testing scenarios including Go unit tests and CLI tool development, examining where AI excels and where human oversight remains critical.
Writing
I write about software engineering, cloud security, and emerging technologies. My focus is on practical insights from working with systems of all sizes, from startup prototypes to enterprise-scale architectures.
Featured Articles
This article explores Model Context Protocol servers and the security challenges they introduce as AI agents gain broader system access. It covers attack vectors, privilege escalation risks, and practical security frameworks for deployment.
This article explains how open-weight models enable organizations to run AI entirely within their own infrastructure, maintaining data sovereignty while leveraging advanced capabilities. It covers deployment strategies and compliance considerations.
More Writing
I regularly publish technical insights on topics including:
Follow me on LinkedIn for updates when new articles are published.