Questions, answered

Security, Data Privacy & Local AI Processing FAQ

Review the answers below for security & privacy workflows in Dynamite Docs. Each answer provides exact details on requirements, boundaries, and best practices.

01

Where is my document data processed?

Hosted and own-key runs send document content to the selected provider. Saved provider keys are encrypted with AES-256-GCM. Browser-only means the source file is not saved in cloud file storage. Hosted and own-key processing sends document content through our server to the selected AI provider. Signed-in extraction results and metadata may be saved to your workspace. Starter, Pro, and Scale can use the signed local Ollama companion for model inference on the computer.

Workflow note: You choose where data flows: use our hosted models for zero-setup convenience, Bring Your Own Key (BYOK) for direct provider billing and enterprise data processing agreements, or run local Ollama models on your machine with 0% external cloud exposure.
02

Can I use my own AI provider keys?

Yes. Every signed-in plan can connect supported provider keys or an OpenAI-compatible endpoint. Free and Starter own-key processing shares the monthly PE allowance; Pro and Scale own-key runs cost 0 PE. The provider bills its own usage and applies its own limits.

Workflow note: We support API keys from OpenAI, Anthropic, Google Gemini, Mistral, Groq, NVIDIA NIM, AWS Bedrock, Azure OpenAI, OpenRouter, and custom OpenAI-compatible proxies. All keys are encrypted at rest with AES-256-GCM.
03

Can I process documents on my local computer?

Yes. Starter, Pro, and Scale include the signed Ollama companion for model inference on your computer. It uses authenticated loopback routes. Local model inference runs on your machine; account, token, and workspace features remain hosted. Pair it with browser-only file storage when the document should not be sent to an external model provider.

Workflow note: The desktop companion routes requests to Ollama on port 11434 via authenticated loopback tokens on port 8756. Document pixels and extracted texts never leave your local workstation.
04

Is my document data used to train AI models?

No. Dynamite Docs never uses your uploaded documents or extracted accounting records to train AI models. Our enterprise API agreements with foundational model providers also explicitly exclude customer data from model training.

Workflow note: Your financial records remain strictly confidential. When you delete files or extractions from your workspace, associated records and cloud storage objects are purged.

Still have questions about document extraction?

Try extracting a real document in our interactive workspace for free, or reach out to our engineering team for custom pipelines.

Can we save optional cookies?

Essential cookies keep you signed in. Optional analytics and masked session replays help diagnose errors. Change your choice in Cookie settings. Privacy policy.