Guides 6 min
Where PR wait time actually sits after you add an AI reviewer
A bot review lands in minutes and the PR still merges a day later. Here is where the wait really is, with the timestamps and a protocol you can run on your own repo.
Topic · 29 articles
Aicodereview
Guides 7 min
AI code review for large PRs: check the input distribution
Vendor benchmarks rank AI code reviewers for large pull requests without reporting the diff sizes they tested. Measure your own PR distribution first.
Guides 7 min
GitHub Copilot code review skips a documented list of files
Copilot code review ships a documented excluded-file list. Every AI reviewer has a coverage boundary, and it changes what your eval measures.
Guides 8 min
AI code review cost per PR is a distribution, not a price
Cloudflare's 131,246 review runs give AI code review a real cost curve: $0.98 median, $3.25 per merge request, and 85% of spend in one tier.
Explainers 8 min
The test harness that detects the agent and lies to it
KillSwitch's interpreter walks the process tree, works out it is talking to a coding agent, then returns a fake error about drawing a pelican instead of the real parse failure.
Best Of 7 min
Best AI Code Review Tools for GitHub Teams (2026)
GitHub's provider path is the most complete one, which is exactly why the shortlist is hard. The GitHub-only tools, the scored directory rows, and five checks to run on your own repos before you buy.
Comparisons 6 min
Kodus vs CodeRabbit: four claims worth re-checking
Both vendors' docs moved since the last comparison you read. Four claims to re-check against the live pages before you pick a reviewer.
Best Of 6 min
Best AI Code Review Tools for a Team on GitLab (2026)
GitLab changes what an AI reviewer can actually do. The provider matrix, the GitLab-capable tools scored against the same nine standards, and seven checks to run on your own merge requests.
Guides 7 min
Martian's Code Review Bench: the "#1" claim rots in months
Two vendors posted "#1 on Martian's Code Review Bench." Both still improved their scores. Both lost first place. How to read the live leaderboard without getting burned.
Guides 6 min
Self-Hosted AI Code Review Tools: What to Verify Before You Deploy
Self-hosting an AI code reviewer moves the data, not the risk. Here is what to verify in the harness before you point it at a real repo, with the receipts.
Comparisons 6 min
Best AI Code Review Tools for Azure DevOps (2026)
An eval-grounded comparison of AI code review tools that actually work on Azure Repos: Copilot code review, CodeRabbit, Qodo/PR-Agent, and Kodus, plus the PAT footgun that silently kills reviews.
Guides 6 min
AI code review's absence blindness: measure what it misses
Teams reviewing a growing volume of AI-generated code need to score what a reviewer fails to notice, not only what it flags. A measurable protocol.
Guides 6 min
Verify your AI reviewer actually follows your team's rules
A canary test, block tests, and independent judging to prove an AI code reviewer actually follows your team's coding standards, not just claims to.
Explainers 5 min
The best AI code review tool is the one the agent built to review with
Trail of Bits spent six months having agents build an LSP, decompiler, static analyzer, and Lean proof model before the Miden review even started. That is where the leverage landed.
Comparisons 6 min
Free AI Code Review Tools: What "Free" Actually Costs You
A hands-on look at what "free" really means across AI code review tools — metered credits, trials, BYO-LLM, and how to evaluate them.
Comparisons 7 min
Pullfrog vs CodeRabbit: don't compare the wrong thing
Pullfrog is a BYOK harness over Claude Code and Codex, not a first-party reviewer like CodeRabbit. Review quality is model-attributed, not harness-attributed. Here's what actually separates them.
Guides 5 min
Reduce Pull Request Review Time With AI: A Reproducible Protocol
Ask the right question: AI review tools cut how long PRs WAIT, not much how long they take to READ. Plus a two-week PR-slice protocol.
Alternatives 3 min
Qodo Merge alternatives: pick the model, not the wrapper
Qodo folded PR-Agent/Merge into one platform. For teams comparing alternatives, the real question is which model + harness you're actually betting on.
Comparisons 3 min
AI code review across many repos: what to actually compare
Eval-grounded guide to comparing AI code review tools for large multi-repo teams, on context-fetching, verification, and permission boundary.
Guides 2 min
Your AI reviewer is judging its own output. That's a blind spot
Teams drowning in AI-generated code often let an LLM review the LLM's own patches. Amazon's judge-correlation work shows why that misses real defects.
Comparisons 2 min
How to evaluate AI review tools for multi-repo teams: an eval-based protocol
Stop comparing marketing claims. An eval-based protocol for picking AI code review tools across many repositories: cross-repo context, verification, permission boundaries.
Comparisons 3 min
AI code review for large multi-repo teams: what actually scales
Eval-grounded comparison of AI code review tools for large teams with many repositories: cross-repo context, verification, permission boundary.
Guides 2 min
Who reviews the AI-generated code before the human does?
The volume of AI-generated code is rising faster than review capacity. The fix starts in evaluation design: don't let the model that wrote the code also judge it.
Explainers 2 min
AI code review reads the patch, not the execution
When AI writes 30% of your lines, patch-text review hits a ceiling. The fix is an execution layer, not a bigger reviewer.
Guides 2 min
Reviewing the surge in AI-generated code: what scales and what breaks
AI is producing more code than teams can review. First-party data on why the old loop breaks (Salesforce, DORA) and what actually scales.
Guides 3 min
Reviewing the volume of AI-generated code: the problem is routing, not speed
AI made PRs smaller but much more numerous. Reviewing the volume isn't a per-PR speed problem, it's a routing problem. Here's how teams actually triage AI-generated code.
Guides 2 min
Fluent but Structurally Wrong: The AI Code Review Failure Mode That Matters
The failure mode that matters in AI review is not missing a bug, it is fluent output that is structurally wrong and easy to trust. How to benchmark for that one specific failure mode.
Guides 2 min
AI code review benchmarks: offline vs online evals
How Martian's Code Review Bench separates reproducible fixed-dataset evals from streaming real-world evals, and the tradeoffs hidden in each.
Explainers 2 min
Reproducing zizmor's flag on the Snowflake injection
I ran zizmor 1.29.0 against the exact Snowflake GitHub Actions workflow. A deterministic static rule flagged the injection at High confidence while AI review cleared it.