1. Overview

Relatch is a free, browser-based document intelligence tool. This Privacy Policy explains what data we collect, why we collect it, and how we handle it. We have built Relatch with a minimal data footprint by design. Your uploaded documents are processed to generate structured outputs and are never stored on our servers beyond the scope of a single session.

By using Relatch at relatch-fe.vercel.app, you agree to the practices described in this policy.

2. What We Collect

2.1 Analytics and Behavioural Data

Relatch uses the following third-party analytics tools to understand how users interact with the product. This data is aggregated and does not personally identify you.

• Google Analytics — collects page views, session duration, device type, and general geographic region.
• Microsoft Clarity — records anonymised heatmaps and session replays to help us identify usability issues. Clarity may capture mouse movements and clicks but does not capture passwords or payment information.
• Google Tag Manager — manages and deploys the analytics tags listed above. It does not independently collect data.

You can opt out of Google Analytics by installing the Google Analytics Opt-out Browser Add-on. You can opt out of Microsoft Clarity by disabling cookies in your browser settings.

2.2 Waitlist Email

Relatch includes an optional email submission form powered by Formspree. If you choose to submit your email address, it is stored by Formspree and will be used solely to notify you when Relatch launches at full scale. We will not send marketing emails unrelated to Relatch. You can request removal of your email at any time by contacting us.

2.3 Uploaded Documents

Documents you upload (PDF, CSV, XML, DOCX, scanned images, and similar formats) are processed client-side where possible. When server-side processing is required, your content is transmitted to third-party AI models solely for extraction and enrichment. We do not store your uploaded files on our servers after processing is complete. We do not use your documents to train any AI model.

3. How Your Documents Are Processed

Relatch uses a multi-stage processing pipeline to extract and enrich content from your documents.

3.1 Text Extraction

• For standard digital PDFs and documents, Relatch uses a built-in PDF.js parser with Engine 3 capability to extract text directly in the browser.
• For scanned or image-based content that requires optical character recognition, Relatch calls Mistral OCR for intelligent character recognition extraction. If Mistral OCR is unavailable, Relatch falls back to OCR Cloud Space, which first applies an OCR layer to your content and then performs extraction.

3.2 AI Enrichment

After extraction, the text is sent to an AI model for enrichment and skill file generation:

• For most documents, Relatch uses Gemini 2.0 Flash Lite (approximately 80% of requests). If this model fails or does not meet the internal quality threshold score, Relatch escalates to Gemini 2.5 Flash for heavier enrichment.
• Relatch includes a document profiler. If your uploaded document is detected as complex or data-heavy, the profiler automatically selects Gemini 2.5 Flash from the start, skipping the lighter model to save time.
• If both AI models are unavailable, Relatch activates a fallback protocol that uses strict internal templates and domain knowledge rules to produce a best-effort output without any external AI call.

Your document content is transmitted to Google's AI services for enrichment. Please review Google's Privacy Policy for details.

3.3 Smart Analyzer

Before any extraction or enrichment begins, Relatch's smart analyzer scans your upload for corrupted files, unsupported formats, and irrelevant document types. Files that do not pass this check are discarded immediately and never transmitted to any external service.

4. Cookies

Relatch uses cookies placed by Google Analytics and Microsoft Clarity for the analytics purposes described above. These are non-essential cookies. You can manage or disable cookies through your browser settings at any time. Disabling cookies will not affect your ability to use the core features of Relatch.

5. Third-Party Services

The following third-party services may process your data as part of using Relatch:

• Google Analytics
• Google Tag Manager
• Gemini AI (Google DeepMind)
• Microsoft Clarity
• Mistral OCR
• OCR Cloud Space
• Formspree (email waitlist only)
• Vercel (hosting and edge delivery)

Each of these services operates under its own privacy policy. We encourage you to review them independently.

6. Data Retention

Relatch does not retain your uploaded documents after your session ends. Analytics data is retained by Google Analytics and Microsoft Clarity according to their respective data retention policies. Waitlist email addresses are retained by Formspree until you request removal.

7. Your Rights

You have the right to request deletion of your email address from our waitlist at any time. To do so, contact us at relatchfe@gmail.com. Because Relatch does not store uploaded documents or personal profiles, there is no additional personal data we hold that would be subject to a deletion request.

8. Children

Relatch does not target children and does not knowingly collect personal information from minors. If you believe a minor has submitted their email address via the waitlist form, contact us and we will remove it promptly.

9. Governing Law

This Privacy Policy is governed by the laws of India. Any disputes arising in connection with this policy shall be subject to the jurisdiction of the competent courts in India.

10. Changes to This Policy

We may update this Privacy Policy as Relatch evolves. When we do, we will update the date at the top of this page. Continued use of Relatch after any changes constitutes acceptance of the updated policy.

11. Contact

For any privacy-related questions, contact us at relatchfe@gmail.com.