We scored 50k PRs with AI – what we learned about code complexity
I'm a CTO with a ~16-person engineering team. Last year I wanted real data on what was actually shipping, not guesswork or story point theater. So we built GitVelocity. Every merged PR gets scored 0–100 by Claude across six dimensions: scope (0–20), architecture (0–20), implementation (0–20), risk (0–20), quality (0–15), perf/security (0–5). Six dimensions added up, then scaled by change size — a 10-line fix scores lower than a 500-line refactor even at the same complexity. Full formula at gitvelocity.dev/scoring-guide. After scoring 50,000+ PRs across TypeScript, Python, Rust, Go,…
We scored 50k PRs with AI – what we learned about code complexity launched on March 30, 2026 with 11 votes, #1,113 of 23,380 launches that month and more than 90% of that year's launches.
In plain words
GitVelocity is a code review scoring tool that uses Claude to evaluate merged pull requests across six dimensions: scope, architecture, implementation, risk, quality, and performance/security. Each PR receives a 0–100 score adjusted for change size, providing engineering teams with objective data on code complexity rather than subjective estimates. Built by a CTO managing a 16-person team, it has analyzed over 50,000 PRs across multiple programming languages including TypeScript, Python, Rust, Go, Java, and Elixir.
written from the facts on this page · September 2026
From the sources
GitVelocity measures engineering velocity with AI-powered commit analysis. See what your team actually ships.
AI reads every merged pull request and puts a number on what you built. Not estimates. Not line counts. Not guesswork. Engineers track their growth. Leaders get data they trust. Whether you're a team of 3 or 300. Connect your GitHub repos. AI analyzes every merged PR across six dimensions of complexity. Get a single score that reflects real engineering output. Track your own velocity over time. See how your contributions are scored. No vanity metrics — just what you shipped. Understand team output without micromanaging. Compare velocity across teams and time periods. Data-driven engineeringfrom gitvelocity.dev
In the maker’s words, at launch
I'm a CTO with a ~16-person engineering team. Last year I wanted real data on what was actually shipping, not guesswork or story point theater. So we built GitVelocity. Every merged PR gets scored 0–100 by Claude across six dimensions: scope (0–20), architecture (0–20), implementation (0–20), risk (0–20), quality…
Does a similar job
all alternatives →
- IBI built a tool to assist AI agents to know when a PR is good to goJan 2026 · dsifry.github.io · ▲45
I've been using Claude Code heavily, and kept hitting the same issue: the agent would push changes, respond to reviews, wait for CI... but never really know when it was done. It would poll CI in loops. Miss actionable comments buried among 15 CodeRabbit suggestions. Or declare victory while threads were still unresolved. The core problem: no deterministic way for an agent to know a PR is ready to merge. So I built gtg (Good To Go). One command, one answer: $ gtg 123 OK PR #123: READY CI: success (5/5 passed) Threads: 3/3 resolved It aggregates CI status, classifies review comments…
GitGuessrFeb 2026 · gitguessr.com · ▲98I built this game as a playful way to train code reading skills. You're dropped into a random location in a real GitHub repo where some lines code are hidden. The goal is to pick up clues from the surrounding code and fill in the missing lines as quickly as possible. It currently has curated game content for Python, TypeScript, JavaScript (by most metrics the top 3 languages on GitHub). I had the idea when it dawned on me that reviewing and understanding code spat out by an LLM is a key skill for the AI era. (I sincerely hope you're critically reviewing what your favorite LLM is serving…
GitHub News, using a peak detection algorithm to detect trending repos2016 · gitlogs.com · ▲184Link RATUKILAT77 menghadirkan panduan lengkap dengan strategi simpel agar peluang menang semakin besar setiap hari. Nikmati pengalaman bermain game slot online dengan sistem modern, akses cepat, dan potensi kemenangan fantastis dari platform gaming terpercaya yang siap bikin cuan makin maksimal.
We built an AI to review your pull requests2025 · infinitcode.ai · ▲53Hey HN, We’re two developers (co-founders) with a team of 20 who got tired of spending hours reviewing PRs, so we built Infinitcode.ai, an AI-powered code reviewer that: - *Summarizes PRs in plain English*: No more deciphering 1,000-line diff jungles - *Catches more than bugs*: Security holes, performance pitfalls, code smells, even typos (yes, we’ll flag “vurnerabilities” and vulnerabilities) - *Zero onboarding*: Works instantly—no “let me learn your codebase for weeks” nonsense. Why we’re posting: We’re in alpha and need brutal honesty. Roast our tool, mock our UI, or tell us why AI will…
MergeAug 2026 · mergeoa.com · ▲115We’re 5 founders who’ve collectively done over 250 interviews - everywhere from startups to Big Tech to quant shops. Most of the interviews we’ve done were Leetcode based or tested skills that weren’t used on the job. These days, with AI, assessments still continue to test code output. Meanwhile, at each of our companies, though, PR counts have nearly tripled. Most of us haven’t manually edited a line of code in a year. Our teams are putting more and more emphasis on code and architecture reviews, yet hiring processes haven’t changed whatsoever. Even the AI-assisted ones we’ve done still…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 21d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 29d ago · world.pixverse.video
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
Littlebird▲709Littlebird remembers everything across your meetings, messages, docs, and apps, then takes action so you can recall any detail and never lose context.
AI · Mar 2026 · littlebird.ai
