Cloud Code architecture and safety layers

He outlines a simple core agent loop, TUI, tooling, and multiple safety layers including sandboxing and classifiers.

Play episode from 46:19

chevron_right

Transcript

chevron_right

Transcript

Episode notes

Brought to You By:

• Statsig — ⁠ The unified platform for flags, analytics, experiments, and more.

• Sonar – The makers of SonarQube, the industry standard for automated code review

• WorkOS – Everything you need to make your app enterprise ready.

—

Boris Cherny is the creator and Head of Claude Code at Anthropic. He previously spent five years at Meta as a Principal Engineer and is the author of the book Programming TypeScript.

In this episode of Pragmatic Engineer, we went through how Claude Code was built and what it means when engineers no longer write most of the code themselves.

We discuss how Claude Code evolved from a side project into a core internal tool at Anthropic and how Boris uses it day-to-day. We go deep into workflow details, including parallel agents, PR structure, deterministic review patterns, and how the system retrieves context from large codebases. We also get into how Claude Cowork was built.

As coding becomes more accessible, the role of engineers shifts rather than shrinks. We examine what that shift means in practice, which skills become more important, and why the lines between product, engineering, and design are blurring.

—

Timestamps

(00:00) Intro

(11:15) Lessons from Meta

(19:46) Joining Anthropic

(23:08) The origins of Claude Code

(32:55) Boris's Claude Code workflow

(36:27) Parallel agents

(40:25) Code reviews

(47:18) Claude Code's architecture

(52:38) Permissions and sandboxing

(55:05) Engineering culture at Anthropic