What we keep. What we don't.

This page explains what GRW does with your data — what we collect, where it goes, what we keep, and what you control. It is the longer version of the brief disclosure shown when you upload a video.

If something on this page is unclear or seems inconsistent with what the product does, that's a bug we want to know about. Email privacy@grwproject.app and we'll fix it.

When you upload a video for analysis, the file may be processed in either of two ways depending on its size, format, and your device's capabilities.

(1) On-device path. The video stays in your browser. Only derived behavioural statistics (facial landmark summaries, blink rates, expression intensities) are sent to our server. The video file itself is not uploaded on this path.

(2) Server-processing path. This is the path when you turn on room mode, add a second camera, the probe finds 20 or more faces, or your browser cannot decode the file. On it, the video is uploaded to a transient processing server, where we extract behavioural statistics plus voice-derived features (pitch, timing, voice quality) and lexical features from the spoken words (e.g. how often you hedge, the variety of vocabulary, sentence structure). The audio waveform and full transcript are processed in memory and discarded immediately afterwards. What we retain in your report is the derived statistical features and a small set of short quoted excerpts (each ≤ 200 characters, capped at 30 per analysis) used as evidence in findings. The original video file is deleted from the processing server as soon as the analysis finishes, and within 60 minutes if the analysis is abandoned or fails.

Your video is deleted from the processing server as soon as the analysis finishes. While the analysis is running we keep it only because the analysis is still reading it, and if an upload is abandoned or the analysis fails it is deleted within 60 minutes. We do not keep copies of it.

The full audio waveform and the full transcript are processed in memory only — never written to durable storage. Only the derived statistical features (lexical density measures, prosody summaries, etc.) and a small set of short quoted excerpts (each capped at 200 characters, capped at 30 per analysis) are retained as evidence in your report.

Behavioural metrics, baselines, and report data are stored against your account so subsequent reports can compare against your personal norm. You can request export or deletion of this data at any time from settings.

You can delete your stored baseline at any time from settings. Deleting it does not delete your reports — it just resets the personal norm we use to anchor future analyses.

You can request export of all your account data (reports, baselines, settings) by emailing privacy@grwproject.app. Exports are delivered as JSON.

You can request deletion of your account from settings. This removes your reports, baselines, and account record. Stored audio / transcript / video have already been discarded post-processing, so deletion is principally about your derived metrics and report history.

Under PIPEDA (Canada) and GDPR (EU/UK), you have the right to access, correct, and erase your data. You can exercise these rights through the channels above.

Privacy questions: privacy@grwproject.app.

Data Protection Officer (GDPR contexts): dpo@grwproject.app.

Security disclosures: security@grwproject.app.