Get evaluated on 6 different axis on how well your AI understands you.
Sample data — your report is computed from your own transcripts.
Trusted by 3,200+ engineers at
Sixteen archetypes
Understand how your AI understands you, and get the insights you need to work better with it. Click any card.
Orchestration · Taste
Many hands, one standard. You fan work out wide and every piece still comes back sounding like it was written by the same person.
Six axes
Orchestration · Velocity
You do not use an agent, you run a formation. Work leaves your hands in parallel and comes back assembled.
Six axes
Planning · Specification
You decide on paper what everyone else discovers in the diff. By the time an agent starts, there is nothing left to interpret.
Six axes
Taste · Velocity
You ship a lot and you throw away almost none of it. The diff is dense and there is nothing in it that is merely filler.
Six axes
Getting the report
01
Claude Code, Codex, opencode, Cursor, Antigravity, Copilot CLI. Nothing to install or turn on.
02
Credentials and your home path go first. The upload aborts if anything slips.
03
Authorize once in your browser; every report lands in your account. Needs 5 sessions or more to score.
Upload · one command, one browser click, done
It reads the AI session transcripts on your computer, then asks whether to score every project at once or just the repo you’re standing in, with the session count for both, before anything uploads. The first run opens your browser once to connect the machine to your account; after that, every report lands straight in your dashboard.
Already ran the command? Sign in to see your report.
Option 1 · recommended
Best for a broader picture across projects. Run it anywhere and choose Global at the prompt — it finds every session on the machine, not just the ones under the folder you happen to be in.
curl -fsSL https://prduck.tryproduck.com/upload.sh | bashOption 2
Best for focusing on a single project. Change into that project’s folder (replace ~/path/to/your-project with the real path), run, and choose This repo at the prompt.
cd ~/path/to/your-project && curl -fsSL https://prduck.tryproduck.com/upload.sh | bashOr let an agent find them
You can use this prompt in Claude, Codex, Cursor, or Antigravity to find all the repos on your machine with agent transcripts, show you the list, and hand back ready-to-run commands for the ones you pick.
Find every repo on my machine where I've used a coding agent. Check ~/.claude/projects, ~/.codex/sessions, ~/.local/share/opencode/opencode.db, ~/.local/share/opencode/storage, ~/.cursor/chats, ~/.cursor/projects, ~/.gemini/antigravity-ide/brain, ~/.gemini/antigravity-cli/brain, ~/.gemini/antigravity/brain, ~/.copilot/session-state. For each repo, list name, absolute path, and total session count. Ask me which ones to include. For each one I pick, hand back this command with the path filled in: cd <ABSOLUTE_PATH> && curl -fsSL https://prduck.tryproduck.com/upload.sh | bash
The command reads agent transcripts under ~/.claude/projects, ~/.codex/sessions, ~/.local/share/opencode/opencode.db, ~/.local/share/opencode/storage, ~/.cursor/chats, ~/.cursor/projects, ~/.gemini/antigravity-ide/brain, ~/.gemini/antigravity-cli/brain, ~/.gemini/antigravity/brain, ~/.copilot/session-state, strips credentials and your home directory on your machine, aborts if anything slips through, then uploads the redacted transcripts so the server can score them. Full prompt, plan and diff text is included in the upload. How that data is handled.
Nominate
