> For the complete documentation index, see [llms.txt](https://documentation.immuta.com/SaaS/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://documentation.immuta.com/SaaS/configuration/application-configuration/reference-guides/immuta-ai-faq.md). # Immuta AI FAQ ## What is Immuta AI, and how is it used within the product? Immuta AI is a suite of AI capabilities integrated within the Immuta platform. It is designed to address the challenges of data access and provisioning at the speed and scale required for AI initiatives and to integrate with Immuta's existing data security and governance workflows. ### Automation Review assist and the Policy explainer Immuta AI features simplify and automate manual workflows and help governance teams scale their role. Their primary functions, which use metadata only (no customer data) and foundational models hosted in AWS Bedrock, like Anthropic Claude, include * **Policy authoring** (Policy explainer) * Generates a summary of the behavior of a policy using mock data to simulate complex, real-world access scenarios * Allows policy authors to verify how a data policy will affect different users * **Data access decision-making** (Review assist) * Automates and streamlines the process of reviewing data access requests * Classifies each request as low, medium, or high risk based on historical patterns, user metadata, and answers to request form questions * Provides an AI-generated rationale for recommended action (approve or deny) ### Compliance The Comply app of Immuta AI enables users to surface what users have access to what and why in natural language prompts. Its primary functions, which use data from the [access summary export](/SaaS/comply/access-summary-export.md) and foundational models hosted in AWS Bedrock, like Anthropic Claude include * **Compliance investigating** (Comply app) * Generates answers to access-related questions within an AI chat window using data from the [access summary export](/SaaS/comply/access-summary-export.md) * Allows governance and audit users to understand current data access granted or revoked by Immuta * Allows governance and audit users to understand future data access granted or revoked by Immuta ### Support The Docs embed Immuta AI feature streamlines user experiences and improves the time-to-answer for user questions by leveraging AI to use the documentation within an AI chat in the product. The primary function, which uses only the public documentation site content and the GitBook Embed feature, is * **Self-service support** (Docs embed) * Uses user prompts to search the documentation site content and provide answers * Allows users to access the documentation site within the Immuta UI where they are completing tasks ## What specific personal or system data elements will the AI system utilize? * Review assist and Policy explainer use metadata (facts about data users, including attributes and groups) and tags (facts about the data, such as classifications and sensitivity levels). For access request recommendations, Immuta review assist analyzes the commonalities in approved users' request form answers, attributes, and groups compared to historical decisions to make a recommendation. * The Comply app uses data from the [access summary export](/SaaS/comply/access-summary-export.md) (facts about data users, tags, policies, access requests, data products, etc.). * The docs embed uses data from the public documentation site and no environment, user, or system data is used. ## Will the Immuta data or prompts be used to train the AI model? No. Immuta's AI features do not use your actual customer data to train or fine-tune the foundational AI model. Instead, these AI features leverage customer metadata (such as group names and attribute names) in conjunction with an external foundational model, like Anthropic Claude, to provide insights and recommendations for managing Immuta itself. The [AWS Bedrock user guide indicates](https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html) that AWS and external parties, including Anthropic, cannot access either the prompts or completions and do not use them for model training. The AWS Bedrock user guide also states that prompts and completions are not stored. ## How long are Immuta prompts, data, and results stored in the AI system? Immuta will log metadata being sent to and responses from the model for debugging purposes. This is metadata Immuta already knows about, so no new information is being generated and stored. ## Can user prompts and AI results be audited? Immuta’s AI only makes recommendations, generates policy summaries, or provides information; if a recommendation is accepted, it is what is audited. ## Are users of the AI system aware that they are interacting with an AI system? Yes. The AI features are explicitly named, such as review assist, and the functionality is described as "infusing AI across the Immuta platform" and offering AI-driven recommendations. Users interacting with features are aware that they are using an AI-powered tool and are a human-in-the-loop, requiring them to accept the recommendation before it takes any action. ## Does Immuta take any steps to mitigate against bias, discrimination, and hallucination, particularly with generative AI? Immuta is not making recommendations that negatively impact a human; they are simply access control recommendations. ## Are humans involved in the AI-augmented decisions? Yes. Human involvement is a key part of the workflow. Immuta AI is described as an "augmentation tool, not a full replacement for humans." While the AI provides policy recommendations and automates access decisions, a "bulk-approval or policy recommendation is green-lighted by the governance team," and humans will still play a crucial role in "setting strategy, defining ethical guidelines, and making high-stakes decisions." The platform provides a "human-in-the-loop" approval process for access requests, as the human reviewer must always accept or deny the recommendation; it does not happen automatically. ## Does Immuta already have similar features or tools that could complete these actions without the need for AI? Yes. Immuta's core data governance and access control features—such as the metadata registry, request/approve workflows, and policy entitlement engine—already address the problems of unified policy-setting and approvals. The AI features, such as review assist, are designed to accelerate and scale these existing governance workflows, transforming manual tasks (like ticket-based approvals and complex policy writing) into automated or natural-language-driven processes. Immuta's AI features leverage foundational models to assist with administrative functions, such as creating access policies, without sharing sensitive customer data with model providers. However, the option to disable the features is available for organizations that want to maintain strict control over all aspects of their data governance workflows. For details about the specific features Immuta offers, see the [Immuta's AI features reference page](/SaaS/configuration/application-configuration/reference-guides/immuta-ai-faq/immutas-ai-features.md). --- # 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://documentation.immuta.com/SaaS/configuration/application-configuration/reference-guides/immuta-ai-faq.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.