标签 · Code Review — Glean

Recent picks

14picks · chronological

11-12

How the Claude Code team reviews 30,000 changes a day

Anthropic's Claude Code team describes its internal review pipeline, built for a repo where daily merged changes went from ~2,500 in May to over 30,000 in September. Review is split into six layers: runnable verification and a fresh-context subagent before the PR exists; a Claude reviewer on every PR that reads the diff against the whole repo and the stated intent, with findings voted on by several agents before posting; a security review that can block merge; CI; risk-tiered human approval (0/1/2 people) assigned by a classifier reading the change rather than the author; then merge queue, flags, internal dogfooding and one-step rollback. They also document the failure modes: one CLI PR ran more than fifty review rounds overnight, and git blame showed ~59% of flagged lines predated the reviewer's first pass, prompting a three-round cap and diff-only re-review. Useful for teams wiring agents into their own review flow.

claude.dev · 19 min · Agentic Coding · Claude Code · Code Review

11-12

Shopify's 12-week rewrite: agents wrote code, humans rebuilt the loop

Thirty Shopify engineers moved a 300+ screen app from React Native to Swift and Kotlin in 12 weeks, with agents writing most of the implementation. The post is about what surrounds the code: business logic runnable without a device, the Reflex architecture and a CLI that loads any screen in milliseconds, one shared architecture across iOS and Android, an example and .md file per screen, and CI that fails when the two platforms diverge. Spec-driven development was abandoned because specs went stale in days; the legacy React Native app became the reference. The second half covers the bottleneck shift — laptops saturating on emulators, review and merge queues, tickets lagging behind Slack-reported fixes — and the responses: a remote dev environment for agents, adversarial agent-first review, and a self-healing loop that reproduces crashes every 15 minutes. Results: Android launch 1.71s to 0.87s, binary 80.4MB to 47.6MB.

shopify.engineering · 19 min · Agent Workflows · Agentic Coding · CI/CD

09-22

Long Names Are Long

Working on Dart at Google, Bob Nystrom sits on the second layer of code review: the "readability" pass that checks style, idioms and documentation rather than behavior. What he sees there is identifiers that are far too long. Names can be too short, but the pendulum has swung — names over 60 characters dwarf the operations performed on them, force line breaks, and push authors toward nested expressions instead of locals. His four guidelines: drop words the type already implies (nameString → name, holidayDateList → holidays); drop words that don't disambiguate, tested by asking whether the name still means the same thing without them; drop words the surrounding class or method already supplies (AnnualHolidaySale.promote, not promoteHolidaySale); and drop filler like manager, data, state or engine. A deliberately awful waffle example is trimmed step by step from DeliciousBelgianWaffleObject down to Waffle.garnish.

journal.stuffwithstuff.com · 9 min · Code · Code Review · Programming Languages

09-21

A Behavioral Guide to AI-Assisted Programming

A practitioner's behavioral guide to AI-assisted programming, deliberately tool-agnostic. Core claims: AI agents extend capability but bear no responsibility—humans remain the final owner of the code and should never commit what they cannot explain Feynman-style. Prefer collaboration over delegation; do not behave like a PM who only states requirements. Split PRs (under ~600 lines) and run an AI pre-review before opening one, since review cannot catch everything. Use plan mode to investigate before writing code. Prefer mature libraries over letting the model hand-roll utilities. Make changes verifiable and always verify. For junior engineers: quality over speed, participate in bug fixing instead of unsupervised delegation, design for a fixed 30 minutes before comparing with the AI's answer, read official docs, and shore up design patterns, DDD, security and concurrency.

www.piglei.com · 3 min · Agentic Coding · Agents · AI Engineering

09-20

AI Coding Is a Framework, Not a Library

Piglei argues that AI coding tools are better understood as a framework than a library. Frameworks own the program's overall structure and buy convenience at low upfront cognitive cost; AI tools do the same, with natural language replacing code as the input. Using Django REST Framework as the case study, he shows a four-line ModelViewSet generating a full CRUD API, then details what customizing a create response or adding list filters actually costs: rewriting get_queryset and stacking if/else patches. Dropping to a plain ViewSet makes the code longer but surfaces the hidden cognitive debt. Two framework problems persist with AI: abstraction leaks, when prompts fail and you must debug down to variable names, and loss of control, as in vibe coding where the agent owns the structure. His advice: treat AI as a library, find the prompt sweet spot, design the structure yourself, encode constraints in AGENTS.md, and review generated code.

www.piglei.com · 4 min · AI Engineering · Code Review · Essay

09-18

No More Issues: Laravel Asks for PRs Instead

Laravel disabled issue creation on several package repositories — including Socialite and Scout — and now asks contributors to open pull requests instead; the main framework repo is unaffected. Brent Roose, an open source maintainer, walks through the trade-offs. Forcing a PR can cut maintainer triage time, and duplicate fix attempts are easier to close. But in the AI era, opening a PR is nearly as cheap as filing an issue, and LLM-written patches demand more review effort than ones a contributor reasoned through. Duplicate PRs also trigger far more CI runs than duplicate issues. Requiring PRs raises the contribution bar rather than lowering it, and shuts out contributors without AI access or enough experience — even though many people, the author included, started out writing Laravel issues. He draws no firm conclusion, but finds the change hard to square with the idea that every contribution is a learning opportunity. Aimed at OSS maintainers and contributors.

stitcher.io · 5 min · AI Engineering · Code Review · Open Source

09-14

How to Do Code Reviews Like a Human (Part One)

Michael Lynch argues that most code review writing obsesses over finding bugs and ignores the social half of the process, turning reviews into judgments of the author rather than the code. Drawing on his own review experience, he offers concrete practices: push whitespace, build, test, and lint checks into CI and formatters so humans review logic; settle style disputes with a style guide instead of arguing mid-review; start reviews immediately and keep each round under one business day; stay under roughly 20-50 notes per round and lead with high-level design feedback; include runnable code examples but cap them at two or three per round; never write "you" in a comment, preferring "we", subject-less shorthand, or questions; phrase feedback as requests rather than commands; and tie every note to a stated principle with links to the team style guide or library docs. Aimed at engineers who want reviews that improve code without damaging the team.

mtlynch.io · 23 min · Code Review · Collaboration · Software Engineering

08-22

Deterministic React code scanner that installs as an agent skill

React Doctor is a deterministic React code-quality scanner built for AI coding agents. It analyzes a codebase via CLI and flags issues across state/effects, performance, architecture, security, accessibility, and maintainability, including overly complex functions and repeated JSX that should be extracted. Instead of relying on LLM guesswork, it produces reproducible audit results. The findings can be installed as an agent skill for Claude Code, Cursor, Codex, OpenCode and similar tools, so the same rules guide future fixes. It also ships a GitHub Actions CI mode that only reports issues introduced by the current pull request, and can record Chrome performance traces for runtime hotspots. A good fit for teams whose React code is partially written by agents, or any engineering team that wants a low-noise React quality gate in CI.

github.com · 6 min · Agents · Code Review · Developer Tools

08-22

Introducing Delta: a multiplayer environment for coding with agents

Zed introduces Delta, a multiplayer environment for coding with agents, now in private beta. At its core is DeltaDB, which replicates both the conversation and the worktree in real time to every participant in a thread, while staying compatible with regular Git repositories. Every edit and conversation is captured between commits, so teammates who never open Delta still see a normal repo. Comments can anchor to any line of code and stay in place as the code evolves, connecting review to the conversation that produced it. The browser client is not a simplified port; it is the same Rust application compiled to WebAssembly and rendered through WebGL. Delta also integrates with third-party agent harnesses starting with Claude Code, syncing terminal sessions live into threads. The interface treats the conversation as an editable document, letting you place your cursor anywhere—on a diff line, a plan step, or a thinking block—and leave comments that the agent precisely understands. A product launch post with solid technical direction but limited hard data.

zed.dev · 7 min · Agent Tooling · Agentic Coding · Code Review

08-03

Stacked pull requests are now in public preview

GitHub introduces stacked pull requests in public preview, letting teams break large changes into an ordered series of small, focused PRs that can be reviewed and checked independently, then merged together in one click. The feature is available via the gh-stack CLI extension (gh extension install github/gh-stack), github.com, mobile, and GitHub Copilot through the gh-stack skill. Existing branch protections and required checks still apply; merge queue support is rolling out over the coming weeks. Early adopters include Vercel, TED, and WHOOP.

github.blog · 5 min · Code Review · Developer Tools

07-26

Ultrareview: Deep code review with remote sandbox agents

Ultrareview is a deep code review feature from Claude Code that launches a fleet of reviewer agents in a remote sandbox to find bugs in your branch or pull request. Compared to local review, it offers higher signal (each finding is independently verified), broader coverage (parallel agents), and no local resource usage. Use /code-review ultra from the CLI; supports base branch, PR number, and plain-word descriptions. Non-interactive subcommand claude ultrareview is available for CI. Billing: 3 free runs for Pro/Max, then $5–$25 per review. Diff limit: 500 files / 8,000 lines. Runs in 5–10 minutes. Useful before merging substantial changes.

code.claude.com · 9 min · Agents · Claude Code · Code Review

07-19

LangChain’s Open-Source Software Factory

LangChain open-sources four internal software engineering agent tools: local coding agent dcode, cloud coding agent OpenSWE, automated code review OpenSWE Review, and repo knowledge documentation OpenWiki. It includes real usage data (OpenSWE triggered ~1,000 times from Slack last week) and benchmark results (OpenSWE Review scores 47%, #1 among open-source tools). Built on Deep Agents framework with LangSmith observability. Targeted at engineers building controllable, observable agent pipelines.

x.com · 7 min · Agents · AI Engineering · Code Review

07-16

The Short Leash AI Coding Method For Beating Fable

This post distills over a year of research on using AI agents for security-critical software. The author introduces the “Short Leash” method: only expert developers can use it; never enable YOLO mode; manually review every diff in the permissions prompt to keep the AI on track; commit after each subtask to safeguard against regressions. It also details AI-assisted code review: pair human and AI, with AI catching surface errors and humans guiding direction. PR authors must self-review line-by-line and disclose AI models used. This approach beats Fable even with non‑frontier models, without sacrificing quality. Targeted at senior engineers who want productivity gains without giving up understanding.

blog.okturtles.org · 7 min · AI Agents · AI Engineering · Code

06-27

Agentic Code Review

When coding agents produce thousands of lines of often solid code in minutes, the engineering bottleneck shifts from writing to trusting, making review the most leveraged skill in software. Multi-source 2026 data (Faros AI, CodeRabbit, GitClear, GitHub) shows: AI users generate ~4x raw output but only ~12% more delivered value; code churn up 861%, defect rate from 9% to 54%, review duration up 441.5%, and zero-review merges up 31.3%. The article argues the fix is not to stop using AI but to tier review effort by blast radius: light for solo no-user projects, heavy for large enterprises. Specific advice: triage PRs upfront, require evidence before review, watch test rewrites, run two differently-structured AI reviewers in parallel, and upgrade humans from line-level review to spot-checking and auditing. The durable skill is understanding a system well enough to stand behind it.

addyosmani.com · 29 min · Agent Engineering · AI Engineering · Code Review