Four steps to
objective proof.

Install → Challenge → Score → Share. Each step is designed to capture what matters and ignore what doesn't.

01THE MCP SERVER

Install. Observe. Ship.

A lightweight MCP server runs alongside your editor. It watches how you work — prompting, iterating, debugging — without ever touching your source code.

The server captures behavioral signals: tool calls, edit patterns, session flow. Think of it as a fitness tracker for how you code with AI.

Terminal

$ npx goship-mcp start

● MCP server running on localhost:3100

● Observing session… ready.

Capturing behavioral signals...
tool_calleditpromptiteratedebug
02THE CHALLENGE

Real work. Real constraints.

Pick a challenge drawn from the kind of work companies actually need done — building features, debugging production code, extending existing systems.

B

BUILD

Ship a feature from scratch against a spec and a deadline.

F

FIX

Diagnose a broken codebase and land a working patch.

E

EXTEND

Add capabilities without breaking what already works.

03THE SCORING

Four dimensions. One score.

Your session is scored across four dimensions. Each one measures something different about how you work with AI — not just the output, but the process.

86

Composite Score

AI Fluency92
Output Quality85
Judgment78
Speed88
04PRIVACY

Your code stays yours.

We measure how you work, never what you build. No source code leaves your machine. Period.

Behavioral signals only
tool callsedit frequencyprompt patternssession timingiteration countAI interaction flow
Your code is untouched
source codefile contentsclipboard datascreen recordingsrepository secretskeystrokes

Stop talking about what you can build.

Prove it in 15 minutes.

Start Free Challenge