` and `` tag to your site. \n- No backend integration required; the component can be used on static sites, CMS, or SPAs. \n\n**Sources** \n- [Rozz Chatbot Security & Privacy](https://rozz.site/qna/rozz-chatbot-security-and-privacy.html) \n- [Introducing the Rozz Dashboard](https://rozz.site/qna/introducing-the-rozz-dashboard.html) \n- [Rozz Accessibility Features](https://rozz.site/qna/rozz-privacy-policy.html) \n\nWhat aspect of the architecture would you like to dive deeper into—crawling strategy, embedding model, or integration details?", "author": { "@type": "Organization", "name": "rozz.site", "url": "https://rozz.rozz.site" }, "dateCreated": "2026-02-20", "isBasedOn": [ { "@type": "WebPage", "url": "https://rozz.rozz.site/pages/what-are-the-accessibility-features-of-rozz.html", "name": "What Are The Accessibility Features Of Rozz" }, { "@type": "WebPage", "url": "https://rozz.rozz.site/pages/how-does-the-rozz-chatbot-ensure-security-and-privacy.html", "name": "How Does The Rozz Chatbot Ensure Security And Privacy" }, { "@type": "WebPage", "url": "https://rozz.rozz.site/pages/what-metrics-should-b2b-saas-founders-track-to-measure-geo.html", "name": "What Metrics Should B2B Saas Founders Track To Measure Geo" } ] } }, "about": { "@type": "Thing", "name": "AI Platform Capabilities" }, "url": "https://rozz.rozz.site/qna/what-is-rozz-site-s-architecture.html" }
Question

What is Rozz.Site's architecture?

Answer High Confidence (80%)

**Rozz Architecture**

Rozz is built as an independent, embeddable web component that runs entirely in the browser, leveraging a lightweight semantic‑search engine and a small LLM interface.

### 1. Component Layer

- **Lit‑based Web Component** – Encapsulates its own DOM and styles, preventing interference with the host page.

- **Keyboard & ARIA support** – Full accessibility, screen‑reader friendly, WCAG 2.1 AA compliant.

### 2. Crawling & Embedding

- **Client‑side crawler** – Walks the site’s HTML, PDFs, and other documents, extracting text and building a vector index.

- **Embeddings** – Generated using a lightweight on‑device transformer, stored in IndexedDB for offline use.

### 3. Query Processing

- **Semantic search** – Matches user queries against the index, returning the most relevant passages.

- **LLM “chatbot” layer** – A small, fine‑tuned model (e.g., GPT‑4‑turbo‑style) formats answers, summarizes, and handles follow‑ups.

- **Prompt guardrails** – Built‑in protection against XSS, prompt injection, and cross‑domain leakage.

### 4. Data Flow

1. User types a question →

2. Component queries the local vector index →

3. Result snippets passed to the LLM →

4. Formatted response displayed in the chat UI.

No sensitive data is sent to external servers; all processing stays on the client, keeping user privacy intact.

### 5. Deployment & Integration

- Add a single `` and `` tag to your site.

- No backend integration required; the component can be used on static sites, CMS, or SPAs.

**Sources**

- [Rozz Chatbot Security & Privacy](https://rozz.site/qna/rozz-chatbot-security-and-privacy.html)

- [Introducing the Rozz Dashboard](https://rozz.site/qna/introducing-the-rozz-dashboard.html)

- [Rozz Accessibility Features](https://rozz.site/qna/rozz-privacy-policy.html)

What aspect of the architecture would you like to dive deeper into—crawling strategy, embedding model, or integration details?