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 info@boostinnovation.ca 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 info@boostinnovation.ca. 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: info@boostinnovation.ca.

Data Protection Officer (GDPR contexts): info@boostinnovation.ca.

Security disclosures: info@boostinnovation.ca.

When you answer a speaker's audience survey, we store your answers for that speaker. The survey uses no video and no biometric data.

The speaker sees the totals. They see notes on what would have made the session better without your name attached, and only once at least four responses are in. They see what you said you will do and the idea you remember, with your first name and organisation, only if you agreed to be quoted. The speaker can share the totals and those quotes with event planners through a link. The speaker can also put one of those quotes, with your first name and organisation, on an image to post publicly, for example on social media. Planners do not see the notes. If the speaker added questions of their own, they see your answers to those without your name attached, and only once at least four responses are in. Planners do not see those either.

Your first name is kept only if you agree to be quoted or to one follow-up email. Your organisation is kept only if you agree to be quoted, and your email only if you agree to the follow-up.

Before any follow-up is sent, we email you once to confirm the address is yours. Nothing else is sent until you confirm, and the follow-up has an unsubscribe link.

If you booked a speaker and they ask you for feedback through GRW Project, we store your answers for that speaker. They see how many organiser responses have come in. They see the figures from organiser answers, and what you booked them to achieve and what you would change without your name attached, only once at least four organiser responses are in. Because the speaker chose whom to send the link to, they may still be able to tell which answers are yours. They see what you would tell another organiser, with your first name and organisation, only if you agreed to be quoted. They see your first name, organisation and email, listed apart from your answers, only if you agreed to be contacted. Your first name and organisation are kept only if you agree to either, and your email only if you agree to be contacted. Planners do not see organiser feedback, and GRW Project sends you nothing.

To ask about or remove your survey details, email info@boostinnovation.ca.