Last Updated: December 29, 2025
At AI CookBook, we are committed to providing a transparent and secure environment for developers to build and deploy AI. This policy explains how we handle data when you use our application to build, convert, run, and serve custom Large Language Models.
We categorize the information handled by the app into two types:
Account Information: If you create an account, we collect your email address and username to manage your saved configurations.
Custom Data Sources: To facilitate fine-tuning, you may upload or point the app to local datasets (JSON, CSV, TXT). Note: Unless you opt-in to cloud-based training, this data remains on your local machine/server.
Hardware Specifications: To provide the "Hardware Cheat Sheet" feature, the app detects your system's GPU model and VRAM capacity.
Usage Analytics: We collect anonymized data on which features are used (e.g., "Build" vs. "Serve") to improve the app's "Recipes."
Technical Logs: In the event of a crash during fine-tuning or model conversion, we may collect error logs containing technical details about the failure.
We use the collected information for the following purposes:
Hardware Optimization: To calculate and display the compatibility of specific models (1.5B, 7B, etc.) with your current VRAM.
Service Delivery: To generate the Python/Flask code required for your custom API serving.
App Improvement: To identify which model architectures (like Qwen or Llama) are most popular and prioritize documentation for them.
AI CookBook operates with a Local-First philosophy:
Model Weights: All .GGUF conversions and LoRA adapters generated by the app are stored locally on your device.
Datasets: Training data used for fine-tuning is processed locally. We do not "scrape" or upload your proprietary training data to our servers unless a cloud-sync feature is explicitly activated by you.
We do not sell your personal information. We only share data with third parties in the following limited circumstances:
Service Providers: We may use third-party analytics (like Google Analytics for Firebase) to monitor app performance.
Legal Requirements: If required by law to comply with a judicial proceeding or court order.
We implement industry-standard security to protect your data:
API Security: Our "Serve" recipes include templates for IP-based rate limiting to help you protect your own deployed models.
Encryption: Any data transmitted between your device and our servers (such as account info) is encrypted via TLS/SSL.
Depending on your location (e.g., GDPR in the EU or CCPA in California), you have the right to:
Access: Request a copy of the data we hold about you.
Deletion: Request that we delete your account and associated usage logs.
Opt-Out: Disable analytics tracking within the app’s settings menu.
We may update this Privacy Policy to reflect changes in AI regulations or app features. We will notify you of any significant changes via an in-app notification.
If you have questions about this policy or how your data is handled within the AI CookBook workflow, please contact us at:
Email: support@quicksolv.app
Would you like me to generate a "Privacy Summary" table to include in your app's "About" section for better scannability?