
Agentic AI
Software engineer with experience building backend services, cloud infrastructure, and AI-powered applications. Over the past few years, I’ve worked across API design, distributed systems, DevOps, and AI workflows, helping take products from idea to production. I enjoy solving engineering problems end-to-end—whether that involves designing system architecture, building reliable backend services, automating infrastructure, or integrating AI where it creates real value. Interests: Backend Engineering, Platform Engineering, Cloud Infrastructure, Distributed Systems, and Applied AI.
Markdown supported · ⌘↵ to post
Julian Neagu
The part about choosing between ReAct and Plan & Execute feels very real. In practice, the simpler loop often wins until the task actually needs a full plan.
Also like the point that these are patterns, not some new kind of magic.