a16z podcast: Can AI run the systems after writing the code?
a16z Podcast · rss · 2026-10-16
a16z General Partner Martin Casado interviews Grepr CEO Jad Naous on what comes after AI writes code: can it also debug and operate production systems?
- Naous says AI transformed his 10-person team, cutting some projects from six months to 10 days.
- Operating production systems is far harder: unpredictable workloads, failures, and countless possible states.
- They explore whether AI can diagnose problems, form and test hypotheses, and debug like a human engineer, plus AI SREs, security, and query optimization.
- A counterintuitive take: the best engineers may gain the most leverage from coding agents.
Core argument: code generation is largely solved; getting AI to understand and operate running systems is the next, harder frontier.
More from coding & agent
- Simon Willison: code mode is the future of tool calling, if it can be sandboxed — springrod · 2026-10-16
- Dev workflow: Astra for tedious tasks, Claude for ideas not implementation — menhguin · 2026-10-16
- Agent named 'Ilya' reportedly scores 1.1pt higher on benchmarks — daniel_mac8 · 2026-10-16
- Gemini CLI fix: substring matching inlined unrequested binary files into model context — priyanshu1976 · 2026-10-16
- Building AI agents on real healthcare claims data: the domain work that makes them work — alex_verem · 2026-10-16
- OpenAI stealth-testing mysterious internal model 'Aeon' in Codex desktop app and Dots — cedric_chee · 2026-10-16