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

# Technical Architecture

<figure><img src="/files/zqW1gwAFXHYsrt63Cd4x" alt=""><figcaption></figcaption></figure>

### Overview

The Cortex AI Agent is built on top of the OpenAI Large Language Model (LLM) and utilizes cutting-edge natural language processing (NLP) and machine learning algorithms to deliver its capabilities.

**- Data Ingestion Layer:** Scans and indexes content from supported sources (markdown files, PDFs, YouTube videos, web pages).

**- Knowledge Graph:** Establishes relationships between content, enabling cross-referencing and context-aware responses.

**- Query Processing Engine:** Uses NLP models to understand user questions and retrieve the most relevant information.

**- User Interface:** Intuitive dashboard for accessing indexed content, conducting searches, and managing integrations.

### Security and Privacy

Data privacy is a top priority for Cortex AI. The system uses encrypted storage for your content and ensures that all data processing is done locally or through secure, private cloud services.

**- Data Encryption:** All stored content is encrypted at rest and in transit.

**- User Control:** Users have full control over their data, with options to delete or export indexed content at any time.

**- No Data Sharing:** Cortex AI does not share your data with third parties.

<br>