What If an AI Agent Was Just a Python Class?

Last Updated on August 19, 2026 by Editorial Team Author(s): Rizwanhoda Originally published on Towards AI. NVIDIA’s new NOOA framework collapses prompts, tools, and state into a single class and it might make you rethink your entire agent stack AI agents have gotten weirdly complicated. After introducing why “simple” agents quickly turn into scattered prompt/tool/state/orchestration systems, the article explains NVIDIA’s NOOA idea: represent an agent as a single Python class where state is modeled via typed fields, prompts live in docstrings, and model-controlled behavior is encoded in specific methods—so capabilities, permissions, and deterministic logic are co-located. It argues this makes state clearer, testing and debugging more natural (especially for deterministic parts), and capability boundaries easier to maintain, while also cautioning that this doesn’t automatically replace graph-based frameworks for complex orchestration needs. It reviews reported benchmark results with caveats, outlines when OO agents are a good fit versus when explicit workflow graphs still win, and closes by reframing the “real question” as how much framework a given agent truly requires—suggesting …