X postClaudeDevsOpinion
Manual line-by-line review becomes impossible at the speed and volume of agentic code generation. This workflow provides an operational blueprint for scaling software delivery through continuous automated review while protecting human attention.
Anthropic's approach treats code review as a multi-layered filter rather than a single approval barrier. By shifting routine bug-hunting, formatting, and behavioral checks to automated subagents with direct verification tools, human intervention is reserved for complex or high-risk changes. Relying on explicit prompt files like CLAUDE.md for repo-specific rules helps address recurring errors at the root, making high-velocity, agent-assisted software development manageable.
ClaudeDevs
@ClaudeDevs · 16 October 2026
Claude writes about 90% of Claude Code's code. From June to September, merged PRs more than doubled while the share reverted fell by more than 40%. We wrote about how we changed code review to get there, and how to adopt it: t.co/9sZe64g3mb
12.6k likes400 replies10k bookmarks1.6m views
View on XSummary generated by AI (Gemini 3.8 Flash, 19 October 2026). It may contain errors – the original source is authoritative.
Similar in content, found by the AI search.
Article:Addy Osmani, Morgan Westlee Lunt, Qing Wang
The Claude Code engineering team explains how they handle code reviews when agents write around 90 percent of the codebase. Instead of exhaustive manual line-by-line checks, they rely on pre-PR verification, automated multi-agent reviews, risk-tiered human approvals, and rapid rollbacks.
Article:Anthropic
Engineers from the Claude Code team at Anthropic share core workflow patterns for shipping code faster, highlighting parallel execution via Git worktrees, plan-first workflows, automated verification, and persistent project memory.
X post:Casey Lee
Casey Lee highlights Anthropic's AI-native SDLC playbook. While agents like Claude Code can generate PRs within hours, traditional security reviews and product sign-offs still take days. Anthropic proposes structuring planning, reviews, and releases into agent-executable steps governed by human checkpoints.
276bookmarks22kviews
Link:Anthropic
The Anthropic Institute shares internal metrics and external benchmark trends demonstrating how AI agents are accelerating the development of subsequent AI models. As of May 2026, over 80% of merged code at Anthropic is written by Claude, with engineers merging 8x more code per day than in 2024. While full recursive self-improvement remains constrained by models' lack of strategic judgement in goal selection, progress is advancing rapidly.
VideoVideo:CURT
In an interview with Ryan Peterman, Thariq Shihipar, an engineer on Anthropic's Claude Code team, discusses how engineering practices are evolving alongside advanced AI models. At Anthropic, developers treat Claude as a thought partner operating at higher levels of abstraction, with manual IDE coding largely diminishing. Shihipar discusses the critical role of harness engineering, loop engineering workflows, verification strategies to prevent incidents, and why foundational technical knowledge remains vital even as coding becomes increasingly automated.
Link:Anthropic
Anthropic introduces Claude Code, an AI coding agent designed for the terminal, IDEs, web, and Slack. The tool maps codebases using agentic search, applies multi-file edits, runs tests, and creates pull requests directly within the developer's environment.
Parts of this content were created with the assistance of AI.
