\n<\/p>\n
When it comes to coding, peer feedback is crucial for catching bugs early, maintaining consistency across a codebase, and improving overall software quality.\u00a0<\/p>\n
The rise of \u201cvibe coding\u201d \u2014 using AI tools that take instructions given in plain language and quickly generate large amounts of code \u2014 has changed how developers work. While these tools have sped up development, they have also introduced new bugs, security risks, and poorly understood code.\u00a0<\/p>\n
Anthropic\u2019s solution is an AI reviewer designed to catch bugs before they make it into the software\u2019s codebase. The new product, called Code Review, launched Monday in Claude Code<\/a>.<\/p>\n \u201cWe\u2019ve seen a lot of growth in Claude Code, especially within the enterprise, and one of the questions that we keep getting from enterprise leaders is: Now that Claude Code is putting up a bunch of pull requests, how do I make sure that those get reviewed in an efficient manner?\u201d Cat Wu, Anthropic\u2019s head of product, told TechCrunch.\u00a0<\/p>\n Pull requests are a mechanism that developers use to submit code changes for review before those changes make it into the software. Wu said Claude Code<\/a> has dramatically increased code output, which has increased pull request reviews that have caused a bottleneck to shipping code. <\/p>\n \u201cCode Review is our answer to that,\u201d Wu said.<\/p>\n Anthropic\u2019s launch of Code Review \u2014 arriving first to Claude for Teams and Claude for Enterprise customers in research preview \u2014 comes at a pivotal moment for the company.\u00a0<\/p>\n Techcrunch event<\/p>\n \n\t\t\t\t\t\t\t\t\tSan Francisco, CA<\/span> On Monday, Anthropic filed two lawsuits <\/a>against the Department of Defense in response to the agency\u2019s designation of Anthropic as a supply chain risk. The dispute will likely see Anthropic leaning more heavily on its booming enterprise business, which has seen subscriptions quadruple since the start of the year. Claude Code<\/a>\u2019s run-rate revenue has surpassed $2.5 billion since launch, according to the company.<\/p>\n \u201cThis product is very much targeted towards our larger scale enterprise users, so companies like Uber, Salesforce, Accenture, who already use Claude Code and now want help with the sheer amount of [pull requests] that it\u2019s helping produce,\u201d Wu said.<\/p>\n She added that developer leads can turn on Code Review to run on default for every engineer on the team. Once enabled, it integrates with GitHub and automatically analyzes pull requests, leaving comments directly on the code explaining potential issues and suggested fixes.\u00a0<\/p>\n The focus is on fixing logical errors over style, Wu said.\u00a0<\/p>\n \u201cThis is really important because a lot of developers have seen AI automated feedback before, and they get annoyed when it\u2019s not immediately actionable,\u201d Wu said. \u201cWe decided we\u2019re going to focus purely on logic errors. This way we\u2019re catching the highest priority things to fix.\u201d<\/p>\n The AI explains its reasoning step by step, outlining what it thinks the issue is, why it might be problematic, and how it can potentially be fixed. The system will label the severity of issues using colors: red for highest severity, yellow for potential problems worth reviewing, and purple for issues tied to pre-existing code or historical bugs.\u00a0<\/p>\n Wu said it does this quickly and efficiently by relying on multiple agents working in parallel, with each agent examining the codebase from a different perspective or dimension. A final agent aggregates and ranks the findings, removing duplicates and prioritizing what\u2019s most important.\u00a0<\/p>\n The tool provides a light security analysis<\/a>, and engineering leads can customize additional checks based on internal best practices. Wu said Anthropic\u2019s more recently launched Claude Code Security<\/a> provides a deeper security analysis.\u00a0<\/p>\n The multi-agent architecture does mean this can be a resource-intensive product, Wu said. Similar to other AI services, pricing is token-based, and the cost varies depending on code complexity \u2014 though Wu estimated each review would cost $15 to $25 on average. She added that it\u2019s a premium experience, and a necessary one as AI tools generate more and more code.\u00a0<\/p>\n \u201c[Code Review] is something that\u2019s coming from an insane amount of market pull,\u201d Wu said. \u201cAs engineers develop with Claude Code, they\u2019re seeing the friction to creating a new feature [decrease], and they\u2019re seeing a much higher demand for code review. So we\u2019re hopeful that with this, we\u2019ll enable enterprises to build faster than they ever could before, and with much fewer bugs than they ever had before.\u201d<\/p>\n<\/div>\n
\n\t\t\t\t\t\t\t\t\t\t\t\t\t|<\/span>
\n\t\t\t\t\t\t\t\t\t\t\t\t\tOctober 13-15, 2026<\/span>\n\t\t\t\t\t\t\t<\/p>\n<\/p><\/div>\n<\/p><\/div>\n<\/div>\n