PromptyQ privacy policy

This server is operated by Dhruv Thakkar. It stores what the PromptyQ VS Code extension captures, to produce reports on how you work with AI coding agents. Questions or requests: thakkardhruv033@gmail.com.

What is collected

Nothing is captured until you run “PromptyQ: Enable Capture” in VS Code. After that, the extension collects: your prompts and the agent's responses; the agent's commands, tool calls and results; a redacted, size-capped code diff of each agent turn; compiler/lint diagnostics and test outcomes; which files you open or scroll, how many lines you type, terminal commands you run, and when the VS Code window gains or loses focus; project name and git remote; your account email. Common secret patterns are redacted on your computer before upload.

How it is used

Only to compute your daily project reports and scores and show them to you. Once per project per day, a compact summary (findings, a few prompts and short code excerpts, never full transcripts) may be sent to an AI model provider (Nebius Token Factory) to review that day's work. The provider processes it to return the review. Data is not sold, not used for advertising, and not used to train AI models.

Who can see it

You. If your account belongs to a team, that team's admin can see your captured data and reports. No other user or team can. Server administrators can technically access the database for operations and security only.

Storage and security

Data is sent over HTTPS and stored on this server. Passwords are stored as salted PBKDF2 hashes, access tokens only as hashes, and tokens expire. Raw captured events are kept until you or your team admin delete them.

Your choices

You can reduce capture (settings promptyq.captureDiffs, promptyq.trackEditorActivity), stop it (“PromptyQ: Disable Capture”), and permanently delete all your data from the dashboard (“Delete my data”). A team admin can also remove a member and their data.