Tag
All content about Review, organized for fast scanning.
Recent developments in code review technologies highlight a trend towards enhanced automation and user control. Upgrades to existing tools now offer varying levels of review depth and improved accuracy, while new open-source solutions facilitate structured feedback through AI integration. Additionally, there is a growing emphasis on incorporating developer oversight and safety measures to streamline the review process and reduce unnecessary prompts.
Boris Cherny argues teams should make agentic coding useful by encoding repeat work into lint rules, CI, tests, and repo docs—not one-off fixes. He suggests files like CLAUDE.md and REVIEW.md so agents can contribute with minimal prompting.
Alibaba has published Open Code Review, an open-source CLI that feeds Git diffs to an LLM agent for structured, line-level review comments. It supports OpenAI- and Anthropic-style setups, custom rules, CI integrations, and an optional local viewer.
Cursor has just rolled out auto-review mode, aiming to reduce approval prompts while keeping agent tool calls safer. A new classifier subagent reviews unsandboxed or non-allowlisted actions, deciding whether to proceed, reroute, or ask you first.
Brendan O’Leary details how Kilo Code is bringing developer oversight back after its v7 VS Code rewrite. Recent updates keep reasoning visible, surface diffs before approval, unify the Changes panel, and improve shell output, permissions, and checkpoint restores.
Clawpatch has just rolled out an automated code review tool that maps repos into semantic work units, not just files. It runs an explicit patch-and-revalidate loop with guardrails, audit trails, and schema-checked provider responses. Defaults to the local Codex CLI.
A recent post by Theodore Ts’o explores an “adversarial review” prompt that pushes agentic systems to scrutinize their own work more skeptically. By using separate subagents and a competitive framing, it can surface more issues than typical self-checks.
Cursor has just rolled out Cursor Security Review, bringing always-on code review and scheduled scanning to Teams and Enterprise. It includes a PR-focused Security Reviewer and a Vulnerability Scanner that can post findings to Slack, with customizable triggers and tooling.
Cursor has just rolled out learned rules for Bugbot, turning real PR feedback into continuously updated review behavior. The company says Bugbot’s suggestions are now addressed nearly 80% of the time before merge, up from 52% at launch.
Vercel has just rolled out OpenReview, bringing a self-hosted AI code review bot to GitHub pull requests. Trigger reviews by mentioning @openreview, get inline suggestions, and even let it commit fixes using Vercel Workflow and Sandbox.