Review take-home codein 60 seconds.

Drop a brief and a GitHub URL — CodeVerdict maps every requirement to code, flags AI shortcuts, and runs the project in a sandbox.

Runs whatever they builtAuto-detected and booted in an isolated VM.
React
Next.js
Vite
TypeScript
Node.js
Express
NestJS
FastAPI
Django
Flask
Go
Rust
Postgres
MongoDB
Redis
MySQL
Docker
Docker Compose
The Problem

Take-home reviews are broken.

Output

A verdict in 60 seconds.

codeverdict.io/assessment/47f3a1b
Assessment
Senior Frontend Engineer
github.com/alex-chen/react-dashboard
Strong Hire
Overall Score87/100
Requirements
92%
Code Quality
85%
Security
91%
AI Detection
8% ✓
Test Coverage
73%
Completed in 47 seconds · E2B sandbox
Git Signal Analysis
2d ago
feat: JWT auth with refresh tokens
a3f8b2c4 files+187/−12
3d ago
feat: Redis session persistence
e91d4a73 files+94/−6
4d ago
feat: rate-limit middleware (60 req/min)
c72f1b32 files+63/−2
5d ago
chore: project scaffold + Vite config
9bd5e4a12 files+340/−0
AI Share · 8% — Low
Consistent commit cadence with incremental diffs. Low perplexity variance. Consistent with human authorship.
Pipeline

Engineered for precision.

Step 01

Ingest requirements

Drop the PDF/Markdown brief. Paste any GitHub URL. CodeVerdict clones it instantly.

Step 02

Headless Execution

Dependencies installed. App booted in a hardened E2B sandbox. Signals captured.

Step 03

Ground Truth Verdict

A scored report with file:line attribution and grounded interview questions.

Core Signals

Technical depth built-in.

Requirement mapping

Automated traceability. Every brief line linked to file:line evidence.

Sandbox VM

Isolation as a first principle. We execute everything in ephemeral E2B environments.

AI detection

Beyond simple matching. We use token perplexity and structural entropy signals.

Plagiarism Detection

Cross-reference submissions against public repositories to identify verbatim copies.

Auditability

Proof, not opinion.

Every verdict is anchored to the source. We provide the file:line evidence for every requirement met, partially met, or missed. No black-box scores.

100%Traceability
E2BHardened VM
Traceability Matrix · Live
80% Match
Implement JWT auth with refresh tokens
Source:src/middleware/auth.ts : 18
Rate-limit /api/* to 60 req/min per IP
Source:src/middleware/rate-limit.ts : 23
Persist sessions to Postgres, not memory
Source:src/db/sessions.repo.ts : 7
WebSocket reconnect with backoff
Source:src/lib/socket.ts : 47 — partial (no jitter)
Tests covering the auth middleware
Source:No test file references middleware/auth.ts
FAQ

Questions, answered.

How long does a verdict actually take?
Most submissions complete in 60 seconds. The agent clones the repo, installs dependencies, boots the app in an E2B sandbox, runs the brief's checks, and writes the report — in parallel. Larger repos with heavy install steps can take up to two minutes.
GitHub repos, zip files, or both?
Both. Paste GitHub URLs (public or private with a token), or upload a zip. CodeVerdict treats them identically: clone, install, run, evaluate.
Which stacks are supported?
Node / TypeScript, Python, Go, plus any Docker / docker-compose project. The agent auto-detects the stack from project hints (package.json, requirements.txt, go.mod, Dockerfile) and picks the right setup path. Frontend SPAs, full-stack apps, and REST APIs all work.
How does AI-code detection work?
Three signals combined: token-level perplexity (LLM-written code has unusually uniform probability distributions), naming and structural entropy, and commit-history analysis (sudden monolithic commits with no incremental work). Output is a 0–100 AI-share score with file:line attribution — no black box.
Is candidate code safe to run?
Yes. Every repository runs inside a single-use E2B virtual machine that is destroyed immediately after the report is generated. Candidate code never touches your machine or CodeVerdict's production servers.
Can I customise scoring?
Yes. Weight requirements, quality, tests, security, and AI-share independently. The verdict (Strong hire / Hire / Maybe / No hire) is computed from your weightings and updates instantly across every past submission.

Stop reading code.
Start hiring engineers.

Free during beta. Join hundreds of technical teams using CodeVerdict to automate their take-home review.