In a new a16z video, Grepr CEO Jad Naous discusses the gap between AI's ability to generate code and its ability to manage running systems. While AI can write production code in minutes, operating real-world systems involves unpredictable workloads, failures, and countless possible states that remain harder to automate.
Naous describes how his 10-person team uses AI coding agents to dramatically accelerate engineering. Projects that once took six months now take roughly ten days. The conversation explores whether AI can troubleshoot production systems by detecting changes, forming hypotheses, and running experiments to diagnose issues.
Naous and a16z General Partner Martin Casado also discuss how the best engineers may gain the most leverage from AI tools, and why security poses a harder problem than code generation itself.
This is an AI-written summary. The original reporting belongs to a16z. How we write these · Spot a mistake?