19 entries
Keyword: code-reviewArticle: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.
From X post: How the Claude Code Team Redesigned Code Review for AI
X post:Coldtea AI
Coldtea AI states that Mermaid diagrams are just the baseline for pull requests, noting that all PRs they ship include an interactive walkthrough.
29bookmarks56.5kviews
X post:ClaudeDevs
Around 90 percent of Claude Code is written by Claude itself. The Anthropic engineering team shares how shifting to automated, multi-layered reviews more than doubled merged pull requests while cutting reverts by over 40 percent.
10kbookmarks1.6mviews
X post:Ohans Emmanuel
Ohans Emmanuel demonstrates how PR Lens integrates with the experimental image capabilities of Jev 1.14 to match pull request screenshots to underlying architecture and data flows in about two seconds.
545bookmarks28kviews
Repository:smarzban/pi-review-panel
pi-review-panel is a TypeScript extension for Pi coding agents that coordinates multi-model code reviews across pinned Git snapshots. It explicitly avoids automated merge verdicts, focusing instead on structured, actionable findings.
16starsTypeScript
From X post: pi-review: Dedicated Code Review Extension for Pi
Link:prlens.dev
An interactive demo by PR Lens illustrates restructuring a sign-up workflow from synchronous email dispatch to an event-driven queue model.
From X post: PR Lens: Interactive Architecture Walkthroughs for Pull Requests
VideoVideo:CURT
Speaking with host Greg, developer Ras Mic details his model-agnostic 'software factory' system. Rather than relying on a commercial platform, the setup consists of five or six markdown files such as agents.md, running an automated four-stage workflow: isolate, build, prove, and ship.
Repository:alibaba/open-code-review
Alibaba has open-sourced OpenCodeReview under the Apache-2.0 licence. The Go-based CLI tool merges deterministic analysis pipelines with LLM agents to deliver precise line-level review comments.
23.7kstarsGo
From Video: Trending GitHub Projects: OpenBao, Magnitude, herdr, and Other Open-Source Tools
Repository:earendil-works/pi-review
pi-review is an open-source extension for the Pi tool that integrates structured code reviews directly into the command-line interface. It analyses uncommitted changes, branches, commits, GitHub pull requests, or directory snapshots to generate prioritised findings and actionable follow-ups.
549starsTypeScript
From X post: pi-review: Dedicated Code Review Extension for Pi
X post:RiverAi7z
RiverAi7z highlights pi-review, an extension developed by the creators of Pi at Earendil, designed to add formal, targeted code reviews to the Pi agent workflow.
1.1kbookmarks54.9kviews
X post:Chris Short
Chris Short highlights the alibaba/open-code-review repository, a code review tool employing a hybrid architecture of deterministic pipelines and LLM agents to deliver line-level comments.
1.9kbookmarks82kviews
X post:Coldtea AI
Coldtea AI announced an open-source tool called pr-lens designed to simplify understanding pull requests generated by AI agents.
7bookmarks208.7kviews
Link:CodeRabbit
CodeRabbit provides a platform for automated AI code reviews on pull requests. The interface snippet demonstrates reviewing code diffs, including permissions and router implementations.
From Video: Agentic Engineering Setup: Kun Chen's Terminal-Based Multi-Agent Workflow
Repository:chaseai-yt/claudex-loop
claudex-loop is a Claude Code skill and plugin that hardens development plans before any code is written. By placing Claude and OpenAI Codex into an adversarial cycle, competing models inspect and challenge specifications to prevent architectural flaws.
1.6kstars
From Video: AI Weekly Updates: Open-Source Model Surge, Agent Harnesses, and Meta's AI Reality Check
Article:Niklas Gruhn
Niklas Gruhn argues against relaying unedited LLM answers in chat threads and code reviews, pointing out that acting as a human intermediary between AI and colleagues destroys value.
From Video: Claude Code: Output-Styles gegen überladene Antworten von Claude Opus 5
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
X post:Itamar Friedman
Itamar Friedman addresses a debate on whether software engineers should inspect and read code produced by AI agents.
459bookmarks62kviews
VideoVideo:Beyond Coding
Amos Haviv, Lead of Developer Workflow teams at Booking.com, discusses the realities of scaling AI engineering tools across 4,000 engineers and 8,000 repositories. While code verification is currently the primary bottleneck, solving it inevitably pushes constraints upstream to product definition or downstream into security and release pipelines.
VideoVideo:Matt Pocock
Matt Pocock announces version 1.1 of his Skills repository, introducing the Wayfinder skill for planning large features, renaming core workflow skills, and establishing an end-to-end development lifecycle from spec to code review.
19 of 19 shown
Do you have an interesting article, a video, or a tweet that belongs in our knowledge base? Write to us at office@webconsulting.at.
Parts of this content were created with the assistance of AI.
