> For the complete documentation index, see [llms.txt](https://docs.toucanai.cloud/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.toucanai.cloud/embed/embedding-overview/embedded-analytics-concepts.md). # Embedded analytics concepts {% hint style="info" %} **Target Audience**: Developers & Non technical users {% endhint %} ### TL;DR Integrate Toucan AI visualizations and conversational assistants directly into host applications to provide contextual data exploration. *** ### When to use this Use this page to understand the architectural relationship between your application and Toucan AI, specifically regarding security, branding, and component delivery. *** #### **Definition of Embedded Analytics** Embedded analytics is the integration of dashboards, charts, and AI assistants into external software, SaaS platforms, or internal tools. This model provides data insights within the user's primary workflow, removing the requirement to access a standalone business intelligence (BI) tool. *** ### **Core Architectural Concepts** Toucan AI utilizes a "separation of concerns" architecture. The host application manages user identity and context, while Toucan AI manages data visualization and AI-driven logic. * **Web Components**: Toucan AI provides embeddable web components compatible with React, Vue, and vanilla JavaScript for front-end integration. * **Security Model**: Access is managed through API keys and tokens to enforce authentication and Row-Level Security (RLS). * **White-Labeling**: Components can be styled to match the host application's branding to maintain a uniform user experience. * **Conversational Interactivity**: End-users can interact with embedded elements through filtering or by using the AI assistant to generate charts via natural language. *** ### Implementation Use Cases Embedding Toucan AI is utilized in environments requiring secure, multi-tenant data delivery: * **SaaS Platforms**: Providing customer-facing analytics dashboards as a product feature. * **Internal Tools**: Surfacing operational data within corporate portals. * **Self-Service Portals**: Enabling users to ask data questions through an embedded AI assistant. *** ### Benefits for Developers * **Reduced Engineering Effort**: Integrate advanced analytics and LLM-powered features without building custom visualization engines. * **Data Governance**: Maintain centralized control over data access and security permissions across all embedded instances. * **Contextual Access**: Deliver data at the point of action, reducing context switching for the end-user. *** ### Constraints * **Authentication Requirement**: Every embedded session requires a valid token to ensure data security. * **Network Visibility**: The host application must have connectivity to Toucan AI services to render components. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## 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://docs.toucanai.cloud/embed/embedding-overview/embedded-analytics-concepts.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.