Privacy Policy

1. Overview

Relatch is a 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. Authenticated users can upload documents which are processed to generate structured outputs intended for use as AI context. We aim to keep our data handling lightweight, reasonable, and transparent.

By using Relatch at app.relatch.online, 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.
• PostHog — records anonymised heatmaps, session replays, and product analytics events to help us identify usability issues and improve the product. PostHog may capture mouse movements, clicks, and page interactions 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 PostHog by disabling cookies in your browser settings.

2.2 Account Information

To upload and process documents, you need an account. Authentication and session management are handled by Clerk. You can sign in using Google OAuth or GitHub OAuth. When you sign in through one of these providers, Relatch receives a basic identity profile (such as your name, email address, and provider user ID) so that we can associate your session with your account. We do not receive your OAuth password.

We use this account information solely to authenticate you, scope your uploads and outputs to your account, and provide essential account-related communication. We do not sell or rent account data.

2.3 Waitlist and Contact Submissions

Relatch uses SplitForms to handle waitlist and contact submissions on the landing page and in-app waitlist prompts. If you choose to submit your email address or a message through one of these forms, that submission is delivered via SplitForms and used solely to follow up with you about Relatch. We will not send marketing emails unrelated to Relatch. You can request removal of your email at any time by contacting us.

2.4 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 and OCR providers solely for extraction and enrichment. We do not retain your uploaded files on our servers beyond what is reasonably needed to deliver the resulting output.

We have opted out, wherever a provider makes such a setting available, of allowing your uploaded content to be used to train or improve their AI models. For example, we have explicitly disabled the training-data option on our Mistral OCR account. For the other AI providers in our pipeline, including Google's Gemini API, we apply the same opt-out posture within the account-level controls those platforms make available to us — but because your content is ultimately processed on each provider's own infrastructure, it remains subject to that provider's own terms of service, technical safeguards, and any changes they make to them, which are outside our direct control. You are responsible for the content you upload, and we encourage you to review the individual privacy policies of the third-party services listed in Section 5.

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 to extract text directly in your browser — no server call is made for these documents.
• For scanned or image-based content that requires optical character recognition, Relatch calls Mistral OCR first. If Mistral OCR is unavailable or does not return usable text, Relatch escalates to Datalab (used sparingly and capped per user per day) as a second OCR pass, and finally to OCR.space as a last-resort fallback if neither of the above succeeds.

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 Google's Gemini API as the primary enrichment model. If this model fails, times out, or does not meet our internal quality threshold, Relatch automatically retries the request through a second, independent AI provider — OpenRouter, routed specifically to Groq's infrastructure — so a single provider outage does not block your generation.
• If both AI providers 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 may be transmitted to Google (Gemini API) and, on fallback, to OpenRouter and Groq, for enrichment. Please review Google's Privacy Policy, OpenRouter's Privacy Policy, and Groq'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 and Session Storage

Relatch uses cookies and similar browser storage for two purposes: (a) analytics, placed by Google Analytics and PostHog as described above; and (b) authentication, where Clerk uses cookies and session storage to keep you signed in and to maintain your session securely. Authentication storage is essential to keeping accounts functional. Analytics cookies are non-essential and you can manage or disable them through your browser settings.

5. Third-Party Services

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

• Clerk (authentication and session management)
• Google OAuth (sign-in)
• GitHub OAuth (sign-in)
• Google Analytics
• Google Tag Manager
• PostHog
• Gemini API (Google) — AI enrichment
• Mistral OCR — primary OCR
• Datalab — secondary OCR fallback
• OCR.space — final OCR fallback
• OpenRouter / Groq — AI enrichment fallback
• SplitForms (contact and waitlist flows)
• 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

We retain account information for as long as your account is active. Uploaded documents are not kept beyond what is reasonably needed to deliver the resulting output. Analytics data is retained by Google Analytics and PostHog under their respective retention policies. Waitlist and contact-form submissions are retained by SplitForms for up to 30 days, or until you request removal, whichever is sooner.

7. Your Rights

You can request deletion of your account, your waitlist email, or any contact submission at any time by emailing us at relatchh@gmail.com. We will action reasonable requests within a reasonable timeframe.

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 relatchh@gmail.com.