Skip to main content
  1. Home
  2. Computing
  3. News

Anthropic adds Code Review to Claude Code to streamline bug hunting

The feature uses multiple AI agents to analyze pull requests, flag potential issues, and provide feedback.

Add as a preferred source on Google
Logo, Text, Symbol
Anthropic

Anthropic’s AI coding assistant, Claude Code, is getting a new feature designed to help developers identify and resolve bugs faster and more efficiently. Aptly named Code Review, the feature automatically analyzes code changes, flags potential issues, and provides actionable feedback before the code is merged.

Anthropic explains that when a pull request (PR) is opened, Code Review “dispatches a team of agents that look for bugs in parallel, verify bugs to filter out false positives, and rank bugs by severity. The result lands on the PR as a single high-signal overview comment, plus in-line comments for specific bugs.”

The company adds that the multi-agent review system scales dynamically based on the PR. It assigns more agents and deeper analysis to larger or more complex changes, while smaller updates get a lighter review. Based on Anthropic’s testing, the system typically completes an average PR review in about 20 minutes.

Recommended Videos

The feature was developed to streamline internal operations after Anthropic saw the amount of code generated per engineer grow by 200% over the last year. The company now uses the system on nearly every PR and reports a significant increase in substantive review comments.

Following successful internal testing, Code Review is now rolling out to Claude for Teams and Enterprise subscribers in research preview. While powerful, the tool is considerably more expensive than lightweight alternatives like the Claude Code GitHub Action, and it is billed on token usage.

Premium pricing for in-depth reviews

Anthropic reveals that code reviews with the new tool average somewhere between $15 and $25, scaling with PR size and complexity. To help admins manage costs, the company is offering monthly organization caps, repository-level restrictions, and an analytics dashboard to track PRs reviewed, acceptance rates, and total spend.

Code Review arrives as Claude Code continues to gain traction commercially. The tool’s run-rate revenue has reportedly surpassed $2.5 billion since launch, more than doubling since early 2026. Furthermore, business subscriptions have quadrupled since the start of the year, with enterprise customers now accounting for over half of Claude Code’s total revenue.

Pranob Mehrotra
Pranob is a seasoned tech journalist with over eight years of experience covering consumer technology. His work has been…
A simple coding mistake is exposing API keys across thousands of websites
Security gaps that are easier to miss than you think
Computer, Electronics, Laptop

After analyzing 10 million webpages, researchers have found thousands of websites accidentally exposing sensitive API credentials, including keys linked to major services like Amazon Web Services, Stripe, and OpenAI.

This is a serious issue because APIs act as the backbone of the apps we use today. They allow websites to connect to services like payments, cloud storage, and AI tools, but they rely on digital keys to stay secure. Once exposed, API keys can allow anyone to interact with those services with malicious intent.

Read more
AMD’s latest Ryzen 9 9950X3D2 pushes X3D to the limit
Dual 3D V-Cache, higher power, and a focus on enthusiast performance
AMD Ryzen 9 9950X3D2 FEatured

AMD has unveiled what might be its most extreme desktop CPU yet, the Ryzen 9 9950X3D2. And it’s going all-in on one thing: cache.

https://twitter.com/jackhuynh/status/2037159705395491033?s=20

Read more
Next-gen AI breakthrough promises chatbots that can read the room better
Researchers are teaching AI chatbots to read between the lines
Generative AI

Have you ever asked a chatbot something and felt like it completely missed your point? You say something with a bit of nuance, and the AI misses the subtlety entirely. That is exactly the problem researchers are trying to solve.

Even though the emotional connection with AI can feel deeper than human conversation for many users, most AI systems today still treat a sentence as a single block of sentiment. If you mix praise and criticism, the nuance often gets lost.

Read more