> For the complete documentation index, see [llms.txt](https://platformdocs.lattica.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://platformdocs.lattica.ai/architecture-overview.md).

# Architecture Overview

The LatticaAI platform enables **secure processing of encrypted computations**, including AI inference workloads, encrypted vector search, and programs. It uses homomorphic encryption and purpose-built acceleration hardware to perform computation without exposing raw data.

The system consists of **client applications** for management and execution, a **backend control plane**, and **hardware accelerators** to perform secure computation.

<img src="/files/SP5puu6UhgOu4ogJn6Gu" alt="Diagram of the main components in the LatticaAI system." class="gitbook-drawing">

## Components

### 1. LatticaAI Clients

<mark style="color:blue;">⫸</mark> The Management Client enables the **Computation Provider** to onboard and manage computations:

&#x20;  <mark style="color:blue;">►</mark> Submit encrypted computations for execution.

&#x20;  <mark style="color:blue;">►</mark> Configure access controls and resource assignments.

&#x20;  <mark style="color:blue;">►</mark> Allocate and monitor compute resources.

After submission, the computation is prepared and registered in the backend, becoming available for secure execution at an assigned execution endpoint.

<mark style="color:blue;">⫸</mark> The **Query Client** facilitates secure interactions with deployed computations.

&#x20;  <mark style="color:blue;">►</mark> It encrypts input data before sending it to the backend for computation.

&#x20;  <mark style="color:blue;">►</mark> The backend processes queries using the homomorphic-ready logic and returns encrypted results.

&#x20;  <mark style="color:blue;">►</mark> The client decrypts the results locally, ensuring data privacy throughout the process.

<table data-card-size="large" data-view="cards" data-full-width="false"><thead><tr><th></th><th></th><th></th><th data-hidden data-card-cover data-type="files"></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>Management Client</strong></td><td>Enables Computation <strong>Providers</strong> to control deployment, manage user permissions, and oversee system resources</td><td></td><td><a href="/files/zPshHASYLP32RdlzS63b">/files/zPshHASYLP32RdlzS63b</a></td><td><a href="/pages/pEVhWbKsWPalGMCO6cmP">/pages/pEVhWbKsWPalGMCO6cmP</a></td></tr><tr><td><strong>Query Client</strong>  </td><td><strong>End users</strong> use this client to access the deployed secured computation.</td><td></td><td><a href="/files/GedAzeqWjCILZucGabbj">/files/GedAzeqWjCILZucGabbj</a></td><td><a href="/pages/DeQLM1YR2UewMJvDwqGJ">/pages/DeQLM1YR2UewMJvDwqGJ</a></td></tr></tbody></table>

***

### 2. LatticaAI **Backend**

<mark style="color:blue;">⫸</mark> **Interaction Manager:** Routes requests to the appropriate encrypted computation.

<mark style="color:blue;">⫸</mark> **Hardware Acceleration:** Currently optimized for GPU-based execution, with a flexible architecture designed to support future hardware acceleration technologies.

***