Privacy Policy
Accounts aren’t available yet. Sign-in is coming soon. Until then, nothing is saved to an account: your CV, applications and progress stay in your browser. The sections about accounts apply once sign-in launches.
Last updated 19 November 2026
- Most of GradDesk runs in your browser, and most of what you do is saved only on your device.
- When the CV Checker runs its AI review, or when you use the AI Matcher or AI feedback on video answers, we send text (never your CV file, video or audio) through our server to Anthropic, the provider of the Claude AI model. Contact details are removed from CV text first. Our AI server functions don't keep that text.
- Without an account, your CV, notes and practice stay in your browser. If you sign in (by an emailed link, no password), we store your email address and sync your saved progress, including your CV text, application notes and interview practice transcripts, in our database (Supabase, hosted in Ireland) until you delete your account.
- We use cookieless analytics (Umami) to count visits and feature use. It never receives your CV, recordings or anything you type.
- We don't sell your data or use it for advertising. You can ask us to see or delete your data at any time.
- Who we are
- What we collect and why
- AI features in detail
- Sensitive information in CVs
- Who we share data with
- International transfers
- How long we keep data
- Cookies and storage on your device
- Your rights
- Age
- Security
- Changes and contact
1. Who we are
GradDesk (graddesk.co.uk) is a free website for UK students and graduates: job listings, a CV Checker, interview practice and assessment practice. It is currently run by Aditya Mysore, a student founder, trading as GradDesk ("GradDesk", "we", "us"). GradDesk is not yet a registered company; registration is in progress, and we'll update this policy when it's complete.
For UK data protection law (the UK GDPR and the Data Protection Act 2018), GradDesk (operated by Aditya Mysore) is the controller of the personal information described here. Contact: hello@graddesk.co.uk.
2. What we collect and why
The law requires a "lawful basis" for each use of personal information. Ours are below.
| What | Why we use it | Lawful basis |
|---|---|---|
| CV text (contact details removed) and, if you paste one, a job advert | To produce the CV Checker's AI review and the AI Matcher's job matches you ask for | Performing the service you request (contract). For any sensitive details in your CV, your explicit consent (see section 4) |
| Interview question wording and transcripts of your spoken answers | Only if you choose "Get AI Feedback" on a video practice session, to write that feedback | Performing the service you request (contract), and explicit consent for any sensitive details you mention |
| Account details (only if you sign in): your email address, and everything the site saves in your browser, synced to your account: CV text, saved jobs, application tracker (including notes and contacts you add), practice scores, CV feedback, video practice notes, transcripts and feedback | To sign you in by email link and keep your progress across devices | Contract. For any sensitive details in your CV or answers, your explicit consent (see section 4) |
| AI feedback records: finished CV reviews, job matches and interview feedback (which can quote short parts of your CV or answers), linked to your account or, for guests, a random device ID | So a retry doesn't use up another review, and to show you your feedback again | Contract |
| Usage data: pages viewed and named feature events (e.g. "practice started"), with approximate country, browser and device type | To understand which features are used and improve the site | Legitimate interests (running and improving a free service), with no profiling of individuals |
| Usage limits and technical records: a random device ID (or your account ID), the time and type of an AI request and its cost, a scrambled (salted and shortened) form of your IP address, and standard server logs, which record request details but not the CV or transcript text you send | To apply fair daily limits on AI reviews, prevent abuse, keep the service secure and fix faults | Legitimate interests |
| Messages you send us by email | To reply and deal with requests, including rights requests and complaints | Legitimate interests; legal obligation for rights requests |
Things that stay on your device and that we never receive: your CV file, and your video and audio recordings. If you don't sign in, your CV text, saved jobs, applications, notes, transcripts and practice scores also stay only on your device (apart from the text sent for an AI review, as described below).
Automated decisions. CV scores, job matches and practice feedback are coaching suggestions. They aren't used to make any decision about you, they aren't shared with employers, and they have no legal or similarly significant effect.
3. AI features in detail
CV Checker
Your CV file is read in your browser. When you check a CV, an AI review runs automatically: the browser first removes your header block (name and contact details), email addresses, phone numbers, links and postcodes, then sends the remaining text (and any job advert you pasted) to a GradDesk server function hosted by Supabase. That function passes it to Anthropic's Claude model, which writes the review and returns it to you. You can see exactly what is sent from the review dialog. The server function doesn't store or log your CV text. We keep a record that a review ran and what it cost, and we hold the finished review for about 24 hours so that a retry doesn't use up another review. If you're signed in, your CV text and the review are also saved to your account (see section 2).
AI Matcher (Find Jobs)
Basic job matching is a keyword comparison done in your browser. If you use the optional AI Matcher, text taken from your CV (contact details removed) is sent the same way, through our Supabase server function to Anthropic, to rank and explain matches. The server function doesn't store or log your CV text; the match results are held for about 24 hours so a retry isn't charged twice.
AI feedback on video answers
Optional. Before anything is sent, you see exactly what will go: the employer and role you chose, the question wording and the text transcript of each answer. Your video and audio are never sent. The server function doesn't store or log your transcripts. The finished feedback, which can quote short parts of your answers, is saved so a retry doesn't use another review. If you're signed in, your transcripts and feedback are also saved to your account. Speech-to-text itself is a feature of your browser (in Chrome, Google's speech service) and is covered by your browser provider's own privacy terms.
Anthropic's use of the data
We use Anthropic's commercial API as our processor. Under its commercial terms, Anthropic processes the text only to provide the service to us and does not use it to train its models. Anthropic may keep API inputs and outputs for a limited period for safety and abuse monitoring, as set out in its terms.
4. Sensitive information in CVs
CVs and interview answers can reveal "special category" information, such as health or disability, religion, ethnicity, sexual orientation, or political or trade union activity (for example through societies, volunteering or a career gap). Please remove anything like this that you don't want reviewed before you add your CV or ask for feedback. By adding your CV to the CV Checker, or sending answers for AI feedback, you give your explicit consent to any such information that remains being processed for that review only. You can withdraw consent at any time by not using the AI features and deleting your saved CVs; this doesn't affect reviews already completed.
5. Who we share data with
We don't sell personal information or share it for advertising. We use these service providers ("processors"), who may only use it on our instructions:
- Supabase: sign-in (Supabase Auth sends the email sign-in links), the database for accounts, synced progress and AI usage records, and the server functions that pass text to Anthropic. Our database is hosted in the EU (Ireland).
- Anthropic: provider of the Claude AI model that writes AI reviews, job matches and interview feedback.
- Netlify: hosting the website, which involves standard server logs such as IP addresses.
- Umami (Umami Cloud): cookieless, aggregated website analytics.
Other services your browser contacts while you use the site, which see your IP address in the normal way:
- Adzuna: some job listings come from the Adzuna API. We send Adzuna no personal information; if you open an Adzuna advert, Adzuna's own privacy policy applies.
- Content delivery networks (cdnjs by Cloudflare, jsDelivr) that serve the code used to read PDF and Word files, and Google's favicon service, used to show some employer logos.
- Employer and other external websites you choose to open from GradDesk. Their own privacy policies apply.
We may also disclose information if the law requires it, or to protect the rights and safety of users or GradDesk.
6. International transfers
Our database is in the EU (Ireland), which the UK recognises as providing adequate protection. Anthropic is based in the United States, and some of our other providers (and their sub-processors) may process data in the US or elsewhere outside the UK. Where personal information leaves the UK, we rely on safeguards recognised by UK law: the UK–US "data bridge" where a provider is certified under it, or otherwise the UK International Data Transfer Addendum to the European Commission's Standard Contractual Clauses, which are built into our providers' data processing agreements. You can ask us for more detail.
7. How long we keep data
- CV text, job adverts and transcripts sent for AI review: not stored or logged by our AI server functions after the response is returned.
- Finished CV reviews and job matches: held for about 24 hours so a retry isn't charged twice, then deleted.
- Interview feedback records: currently kept until you delete your account or ask us to delete them (guests can ask us too). We're adding automatic deletion and will update this policy when it's in place.
- Usage-limit records (device or account ID, scrambled IP, time and cost of a request): up to 12 months, to manage costs and prevent abuse.
- Account and synced progress (including CV text, notes and transcripts): until you delete your account, using "Delete my account" in the site, or ask us to. Deleting your account removes your synced data straight away.
- Analytics: aggregated statistics, kept for as long as they're useful.
- Emails to us: up to 2 years after the matter is closed, unless we need them longer for a legal reason.
- Data on your device: stays until you delete it in the site (for example "Remove this CV") or clear your browser's site data.
8. Cookies and storage on your device
GradDesk doesn't use advertising or tracking cookies. Umami analytics is cookieless. We use your browser's local storage and IndexedDB to keep what you ask the site to save (CVs, saved jobs, applications, practice progress, settings and, if you sign in, your login session). This storage is strictly necessary for features you request. We also store a small flag recording whether you've completed your first useful action, which is used only for statistics. You can clear all of this at any time through your browser's settings.
9. Your rights
Under UK data protection law you have the right to:
- access the personal information we hold about you;
- have inaccurate information corrected;
- have your information deleted;
- restrict or object to our use of it, including use based on legitimate interests;
- receive information you gave us in a portable format;
- withdraw consent at any time, where we rely on consent.
To use any of these rights, or to make a complaint about how we handle your data, email hello@graddesk.co.uk. We'll acknowledge complaints within 30 days and respond to requests within one month. If you're signed in, you can delete your account and all synced data yourself with "Delete my account". Data that's only on your device can't be seen or deleted by us, but you can delete it yourself in the site or through your browser.
If you're unhappy with our response, you can complain to the Information Commissioner's Office (ICO): ico.org.uk/make-a-complaint or 0303 123 1113.
10. Age
GradDesk is designed for university students and graduates, and is intended for people aged 18 and over. Please don't create an account or use the AI features if you're under 16. If you think someone under 16 has given us personal information, contact us and we'll delete it.
11. Security
We use HTTPS throughout, keep API keys on the server rather than in your browser, remove contact details from CV text before it's sent for AI review, and use database access rules so each signed-in user can only reach their own data. No online service is completely secure, so please don't include information in your CV or answers that you aren't comfortable having reviewed.
12. Changes and contact
We'll update this policy when our services or providers change, and change the date at the top. If a change is significant we'll make it clear on the site. Questions: hello@graddesk.co.uk.