> 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/model-cards/overview.md).

# Overview

Model cards describe the AI models and supporting components used in Nested Knowledge. They document each tool's intended use, inputs, evaluation, limitations, and human oversight requirements.

Cards are grouped by the review stage they support. Start with the module below that matches the tool you're reviewing, or use this page as a full directory. Review each AI tool before use in a review.

| Module                                                                                   | Covers                                                                    |
| ---------------------------------------------------------------------------------------- | ------------------------------------------------------------------------- |
| [Literature Search](/ai-transparency/model-cards/literature-search.md)                   | Query drafting and citation import                                        |
| [Screening](/ai-transparency/model-cards/screening.md)                                   | Criteria answering, dual-reviewer automation, criteria/hierarchy drafting |
| [Tagging & Extraction](/ai-transparency/model-cards/tagging.md)                          | PICO tagging and evidence extraction                                      |
| [Meta-Analytical Extraction](/ai-transparency/model-cards/meta-analytical-extraction.md) | Quantitative data extraction and harmonization                            |
| [Critical Appraisal](/ai-transparency/model-cards/critical-appraisal.md)                 | Risk-of-bias and quality assessment                                       |
| [Synthesis](/ai-transparency/model-cards/synthesis-exports.md)                           | Narrative and data-driven output generation                               |

### PALISADE Checklist Alignment

Every model card already addresses each domain in the ISPOR **PALISADE Checklist.** If you're checking a card against PALISADE directly, use this table to find which section covers which domain.

| PALISADE                  | Section covered         |
| ------------------------- | ----------------------- |
| Purpose                   | Overview, Intended Use  |
| Appropriateness           | Intended Use            |
| Limitations               | Limitations             |
| Implementation            | Training Data           |
| Sensitivity & Specificity | Evaluation              |
| Algorithm Characteristics | Overview, Training Data |
| Data Characteristics      | Training Data           |
| Explainability            | Ethical Considerations  |


---

# 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/model-cards/overview.md?ask=<question>&goal=<user_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.