---
title: Quoting Boris Cherny
link: https://simonwillison.net/2026/Sep/11/boris-cherny/
source: simonwillison-net
published: 2026-09-11T17:47:11Z
updated: 2026-09-11T17:47:11Z
first_seen: 2026-09-11T20:54:13.322731864Z
labels:
- agentic-engineering
- ai
- ai-assisted-programming
- anthropic
- boris-cherny
- claude
- claude-code
- coding-agents
- generative-ai
- llms
summary: 'Production code written by Claude should have a higher bar than if it was written by a human. At Anthropic, we have many guardrails in place to make sure this is happening: lots of lint rules, lots of tests, Claude-driven end to end tests, Claude-powered fuzzers running daily, automated code reviews and security reviews, automated code refactoring, and so on. Without these, you can end up with a mess that is hard to maintain down the line. — Boris Cherny Tags: claude, ai, claude-code, llms, coding-agents, ai-assisted-programming, generative-ai, agentic-engineering, boris-cherny, anthropic'
content: extracted
html: 2026-09-11-quoting-boris-cherny.html
---

> Production code written by Claude should have a higher bar than if it was written by a human. At Anthropic, we have many guardrails in place to make sure this is happening: lots of lint rules, lots of tests, Claude-driven end to end tests, Claude-powered fuzzers running daily, automated code reviews and security reviews, automated code refactoring, and so on. Without these, you can end up with a mess that is hard to maintain down the line.

— [Boris Cherny](https://twitter.com/bcherny/status/2098217573276131577)