# Computation Layer (AI) AI privacy is often overlooked in modern stacks. Most AI tools run in the cloud and log every prompt, response, and interaction. Invinos takes a radically different approach: computation is handled locally using on-device models. Local language models (LLMs) are optimized to run efficiently on modern mobile hardware using quantized weights and GPU acceleration. These models never connect to the cloud. Prompts are encrypted and isolated at runtime, and no inference data is stored after execution. This allows users to reason, generate, and explore with AI without exposing their thoughts, questions, or intentions to any server. In the future, this layer will support encrypted prompt chains, collaborative agents, and smart contract execution. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://invinos.gitbook.io/invinos/system-architecture-overview/core-design-layers/computation-layer-ai.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.