> For the complete documentation index, see [llms.txt](https://docs.ovaledge.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.ovaledge.com/ai/askedgi/security-and-privacy.md). # Security & Privacy Security and privacy form the foundation of askEdgi’s design. Since askEdgi connects directly to enterprise systems and processes sensitive business data, every interaction follows strict architectural safeguards, compliance controls, and governance policies. ## Secure Architecture **Direct, Controlled Access**: Direct connection to enterprise data sources without creating permanent data copies. **Temporary Workspaces**: The required data is pulled into a secure workspace for analysis and then discarded once the session ends. **Hybrid AI Model**: Governance-aware in-house layer generates queries; trusted external LLMs (e.g., OpenAI) handle language understanding. Sensitive enterprise data is never sent to external models. **Retrieval-Augmented Generation (RAG):** Only metadata and summaries are shared with the LLM; raw enterprise data remains within the enterprise environment. ## Data Privacy & Protection * **No Model Training on Enterprise Data:** Data is used only for in-session processing, not model training. * **PII & Sensitive Data Handling**: Metadata classification detects sensitive fields and enforces restrictions. * **Encryption Everywhere**: Encryption in transit and at rest, with strict authentication for authorized access. * **Role-Based Access Controls (RBAC):** Governance permissions validated before every query, ensuring users see only entitled data. ## User Controls * **Fine-Tuned Queries:** AI-generated queries can be refined or overridden for accuracy and compliance. * **Admin Configurations:** Logic templates, recipes, and AI behaviors can be configured to align with governance standards. * **Access Transparency:** Complete visibility into what data is accessed, how it is used, and by whom. ## **Why askEdgi is Different** * Raw data is never exposed to public AI models. * Governance-first principles are enforced before delivering results. * Real-time insights are provided without the need for ETL or permanent data movement. * Secure scalability is supported across Public, SaaS, and On-Prem deployments with full compliance. *** Copyright © 2025, OvalEdge LLC, Peachtree Corners, GA USA --- # 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, and the optional `goal` query parameter: ``` GET https://docs.ovaledge.com/ai/askedgi/security-and-privacy.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. 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.