> For the complete documentation index, see [llms.txt](https://docs.nested-knowledge.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.nested-knowledge.com/ai-transparency/ai-in-nested-knowledge/ai-transparency.md). # AI Transparency Learn how Nested Knowledge uses transparent, human-supervised AI to accelerate literature reviews. Nested Knowledge uses artificial intelligence (AI) to help research teams conduct faster, more rigorous systematic reviews. Our AI-powered evidence synthesis tools support literature search, screening, data extraction, critical appraisal, and reporting. AI assists researchers. It does not replace their judgment. Researchers review AI-generated outputs and retain responsibility for every review decision. ### Transparent AI For Evidence Synthesis We design AI features for transparency, traceability, and human oversight. Each feature is optional and requires user action. Researchers can review, edit, or remove AI-generated outputs before using them. AI tools can support: * Systematic literature searches and Boolean search strategy development * Study screening and eligibility assessment * Data extraction, critical appraisal, and evidence-backed insights And many more. This approach helps teams streamline biomedical evidence synthesis without losing control of their methods or findings. ### Responsible Use Of AI In Systematic Reviews Nested Knowledge supports responsible AI use in secondary medical research. AI features operate on research data selected by users. AI outputs remain connected to their source records wherever applicable. We do not use customer data to train or update our AI models with the exception of Robot Screener. Full-text processing is limited to the requested workflow. AI-assisted decisions remain auditable within each project. ### AI Tools For Research Teams Nested Knowledge combines AI and machine learning with structured review workflows. Tools such as Smart Search, Robot Screener, Smart Tags, Smart Critical Appraisal, and Smart Insights help teams work efficiently across the evidence-review lifecycle. Every feature supports researcher-led, transparent systematic reviews. This keeps methods reproducible and findings grounded in the underlying evidence. ### Important Links


Overview Of AI Tools	See where each AI-assisted tool fits in your review workflow.	Overview of AI Tools
Validation Studies	Review evidence evaluating Nested Knowledge AI tools.	Validation Studies
RAISE Compliance Guide	Plan human oversight and validation for AI-assisted reviews.	RAISE Compliance Guide
AI Compliance With Legislation	Understand Nested Knowledge’s AI legislation compliance policy.	Artificial Intelligence (AI) Compliance with Legislation
NICE Compliance Guide	How Nested Knowledge aligns with UK standards for clinical evidence.	https://about.nested-knowledge.com/2024/09/01/nice-guidelines-for-ai-methods-the-nested-knowledge-approach/
Use Cases	Real-world applications across the evidence synthesis life cycle.	https://about.nested-knowledge.com/evidence-synthesis-for-life-sciences-organizations/
Disclosure Of AI Systems	Review each tool’s data use, model, and human oversight.	Disclosure of AI Systems in Nested Knowledge
Use Of Metadata, Abstracts, And Full Texts	Check AI-use restrictions before importing published study materials.	Copyright and AI-Use Restrictions on Imported Texts
Model Cards	Review intended use, evaluation, limitations, and human oversight.	Overview

--- # 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 by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.nested-knowledge.com/ai-transparency/ai-in-nested-knowledge/ai-transparency.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. 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.