PRIVACY
Small inputs, clear boundaries.
AngleCue receives the public TikTok URL, audience, product type, goal and available filming material you select, plus optional written details. Optional transcript and on-screen text are used to complete that report. A Google profile is received only after you choose to sign in.
What is sent?
The analyzer request can contain a public TikTok URL, audience, optional product context, goal, available filming material, transcript or on-screen text. If you request a revision, we also receive the selected draft reference, change reason and correction choices. Copy and review events record the analyzer surface, report and draft references, draft number, judgement and selected change reason. Revision records link the new report to its parent. These events do not send the draft text or private rewrite context and do not confirm adoption, filming or results. Product events contain a random visitor ID, a short session ID, the page path, coarse UTM values and event properties. The optional hook game records anonymous visits, choices, completion, copy actions and clicks to the analyzer. It does not send the nickname, share text or full page URL. When Google sign-in is available and you choose to use it, we receive your Google account identifier (subject), email address, name and profile picture URL, where supplied. We do not ask for passwords, payment details, private account cookies or contact lists.
How is the input used?
Public-link metadata is fetched through a protected server-side connector. In manual text mode that lookup is skipped. When you request model-assisted suggestions, your supplied text and product context, available post description and published subtitles are sent to the configured model provider through our server. A requested revision uses the original report context and your explicit correction choices. The browser never receives provider keys. Do not paste secrets, private customer data or confidential source code into the form.
Model providers: AI features use Z.ai (api.z.ai), except the video analyzer’s reference breakdown, which is sent to DeepSeek (api.deepseek.com) and to Z.ai only if DeepSeek does not return a usable answer. For that breakdown we send only the video’s post description and published subtitles, or the transcript and on-screen text you supplied; not the TikTok link, your product context, visitor ID or account details. DeepSeek processes the request under its own privacy policy and may process it on servers in the People’s Republic of China.
Transcript generator: when a public TikTok video up to 3 minutes long has no published subtitles, our server fetches that video’s file from TikTok’s content network and passes it, without storing it, to OpenRouter (openrouter.ai), which sends it to DeepInfra for speech recognition. The upload contains the video file named by its TikTok video ID; not the TikTok link, your visitor ID or account details. OpenRouter and DeepInfra process it under their own privacy policies. The resulting text is shown as an AI transcription and may contain recognition errors.
The optional AI tools on guide pages send your selected product category and audience, plus an anonymous visitor identifier for allowance protection. Text entered into those guide pages stays in the browser to fill the product-name slot. For a fresh three-draft analyzer result, an AI filming check starts automatically: the drafts’ opening lines and filming notes, and the associated product, audience and available-material context, are sent through our server to the model provider. This check uses additional free allowance and is separate from the original generation. If you choose to change a shot, your selected material and draft context are sent for that requested revision. These proposals do not verify product claims, material rights or your ability to film. The confirmed-product-page script flow is a separate process and does not automatically start this three-draft check.
What is stored?
The prototype stores browser visitor identifiers, server-side daily usage counts, hashed request identifiers and short event records for funnel measurement. Research logs record a hash of the query or source link and the operation status. Limited report diagnostics record service status, attempt counts, timing and available usage totals, without source text or your brief. Public video descriptions, counts, published subtitles and AI transcriptions of public videos may be cached and reused for up to 24 hours; that cache does not contain your audience, product context, supplied text or generated advice. This temporary public cache is separate from transcripts you explicitly choose to save to your private account. Daily allowance protection uses a server-side keyed hash of the request IP and anonymous visitor ID; raw IP addresses are not written to these usage tables.
When revision is enabled for a completed report, we store an encrypted snapshot of its original input, source text, brief and drafts, with a 64 KiB limit and a 24-hour expiry. Short-lived encrypted revision results allow the same submission to be retrieved without starting another model request. Expired content cannot be used for revisions and is removed during subsequent cleanup requests. A secure, HTTP-only cookie binds anonymous revision access to the browser that received the report. Private rewrite references stay out of analytics, URLs, copied drafts and Markdown exports.
Operation references, hashes, limited correction choices, allowance records and execution status may remain after content expiry to prevent duplicate execution and reconcile uncertain results. They do not contain the source text, private brief or draft body.
When confirmed-task preparation is enabled, a submitted product-page link lets our server read available public page text and send relevant passages to the configured model provider to prepare a task for your review. Source, proposal and confirmed-task content is stored encrypted and is valid for no more than 24 hours from the original source capture. When free previews are enabled, confirming the task requests one model-generated preview of the confirmed product statements. That same request may include the accepted reference quotes and their expression labels to explain the proposed opening. The explanation is AI advice, not verification of audience fit or performance; no additional explanation request is started. Only a validated explanation is retained with the encrypted preview and saved task; unavailable explanations are not filled in later. Its encrypted result expires no later than that task; uncertain execution is kept as a status record to prevent another model request. Preview generation does not require Google sign-in or a purchase. Expiry prevents further use; clearing stored content depends on later cleanup, and user-linked operation references and status records may remain.
Customer-task measurement uses a random measurement reference to connect a confirmed task, its preview, saved-account readback and copy or download requests. These measurement references do not authorize access to your task. The short records contain finite action names, event and action identifiers, source classification, status, timing and available usage totals; they do not contain product text, generated scripts, image bytes, Google profile fields or private task-access references. Copy success describes the browser clipboard API response; a download request does not confirm a saved file or adoption. Measurement references and status records may remain after the original task expires; this does not extend access to its content.
When customer product-image capture is enabled, the server may retrieve one static JPEG, PNG or WebP image linked in the public product page, up to 256 KiB. Captured image bytes are stored encrypted, bound to the original task and accessible only through its authorized browser or saved account. They expire with the original task within 24 hours; opening or saving a task does not extend that expiry. Confirmation asks whether you can use the displayed image. The model receives the permitted material description rather than the image bytes; this does not perform image interpretation or OCR, verify ownership or establish product results. Expiry prevents further access and does not promise immediate physical deletion.
When task continuation is enabled and you choose to keep a task, browser session storage holds opaque task references, operation identifiers, consent, status and expiry. These references are valid for up to 30 minutes. It does not hold your Google profile, source text or brief. Canceling the continuation does not delete the server task.
Google sign-in and saved work
When Google sign-in is available, your Google account identifier identifies a returning account. Your email, name and profile picture URL are used to display your account. Some seller-tool results can be saved automatically when you are signed in, as described below; other reports and tasks are associated with your account when you choose to save them. Video analyzer reports are saved to your account when you choose to save them. These profile fields, account creation and update times, and a hashed app session token are stored in the account database. Google access tokens are used temporarily to retrieve your profile and are not persisted by this sign-in implementation.
The browser may load your profile image from its image host without sending a page referrer. Your Google account identifier, email, name and profile image URL are not automatically included in model prompts, public-link lookups or product analytics.
A report saved to your account, whether automatically or at your request, can include its source link, summary and report payload, such as supplied product context, filming material, transcript, screen text and generated drafts. We do not currently apply an automatic deletion deadline to Google profile records or saved report history. The 24-hour public-evidence cache and task expiry do not apply to that history.
Saved transcripts: after you sign in, choosing Save transcript stores the video link, public author and caption, subtitle language, published-subtitle or AI-transcription source, truncated-result flag, subtitle text and timed lines, and save/update times with your account. Anonymous extractions are not automatically added to an account, and signing in alone does not save a transcript. These saves are private account records, with no public sharing link. We do not currently apply an automatic deletion deadline to saved transcripts. You can delete individual saves under Account → Transcripts; signing out does not delete them. The separate public-video cache may still contain public subtitles or AI transcriptions for its stated cache period.
App sessions expire after 30 days. Signing out ends the current session; it does not delete the profile stored by AngleCue, saved reports or server tasks. Self-service account and report deletion is not available yet.
Seller tools
The TikTok Shop comment analyzer receives the category, price band and keyword or product link you choose. Our server fetches public TikTok videos, comments and reviews for it through a third-party data provider and sends public comment text to the configured model provider to sort it; the browser never receives provider keys. A finished map is kept for 30 days so you can reopen it, linked to your account when you are signed in or otherwise to a random browser cookie. When you are signed in, a newly completed map may also be saved automatically as a report in your account history; that saved report has no automatic deletion deadline. Reopening a map or viewing a sample does not by itself save it as a report.
The creator sample check receives the creator handle and the choices you make. When you are signed in and a new batch has successful results, we attempt to save those results to your account history automatically; failed and unexecuted checks are not included. If that save fails, you can retry. If you are signed out, you may choose to save and sign in; on return we attempt to save the result without running the checks again. A separately continued pending check is not automatically saved as a report by that continuation. Public profile and post statistics are fetched the same way and cached for up to 24 hours under a keyed hash of the handle; the cache and our usage counts do not store the handle itself. To prevent duplicate check charges, a pending check is kept in this browser until its outcome is confirmed; it includes the handle and selected choices. Our server keeps an operation reference, account identifier when signed in, a keyed input fingerprint and allowance status. The operation can retain public statistics for up to 24 hours for replay; expired statistics are cleared during later cleanup, while the operation record remains to prevent duplicate execution. If you track a sample, the creator handle, product name, sent date, the result you report and any sample-content confirmation you choose to make are stored with your account, and our server schedules checks of the creator's recent public videos for 21 days after the sent date, or until day 90 if you mark the sample refundable (every 3 days after day 21). Checks may be delayed or unavailable; you can stop tracking earlier. The tracking window is not a platform deadline. Sample records and check results remain in your account after checks end; we do not currently apply an automatic deletion deadline to them.
Payments
AngleCue Pro is sold through Paddle (paddle.com), the merchant of record. Card and billing details are entered on Paddle's checkout and are never sent to AngleCue. We receive and store your Paddle subscription and customer identifiers, subscription status and billing period dates, linked to your AngleCue account, and we count your Pro usage per billing period. Paddle receives your email address to create the checkout and send receipts; its own privacy policy applies to the payment.
Product analytics
AngleCue measures its own pages with first-party product events sent only to anglecue.app. These first-party events set no analytics cookies. While you are signed in, our server uses your existing app session to associate new first-party product events with your AngleCue account. Anonymous history is not assigned to your account, and the optional hook game stays anonymous. We also retain the first browser-reported acquisition snapshot observed while signed in: coarse campaign tags, referring hostname and landing pathname, without the query string. It may be incomplete and is not a verified referral or signup source. The random visitor ID, short session ID and coarse UTM values described above are kept in your browser’s local storage; clearing site data resets them. The events do not contain your tool inputs, generated scripts or Google profile fields.
We also use Cloudflare Web Analytics, a cookie-free, privacy-focused measurement service run by Cloudflare, our hosting provider. When you view a page in a browser, Cloudflare adds its measurement script, which records page views and performance metrics such as page load time. It does not use cookies and does not track you across sites. See Cloudflare Web Analytics and the Cloudflare Privacy Policy.
Google Analytics
We also use Google Analytics 4, a Google service, to see how our pages are used. After a page has finished loading, your browser loads Google’s analytics script on every page, including the Pro checkout pages. It records page views (the page address with only campaign tags such as utm_source kept, the referring site’s domain and the page title) and a few key actions: starting a tool, getting a tool result, showing interest in Pro and saving a result. Those key actions carry only the name of the tool page. We do not send your tool inputs, TikTok links, transcripts, generated scripts, email address, Google profile fields, payment details or saved-task references to Google Analytics.
Google Analytics sets its own cookies on anglecue.app (such as _ga) to tell browsers and visits apart, and Google receives your IP address to provide the service. Google signals and ad personalization are turned off, and we do not use this data for advertising. Google Analytics is not loaded when your browser sends a Global Privacy Control signal. You can also block it with the Google Analytics opt-out browser add-on. Google processes this data under the Google Privacy Policy.
Privacy questions
Contact support@anglecue.app privately about your account, saved work or privacy questions. Please do not send passwords, access tokens or payment details.