> 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/best-practices/compliance-guides/raise-compliance-guide.md).
# RAISE Compliance Guide
Responsible use of AI in evidence SynthEsis (RAISE) helps you plan human oversight, validation, and reporting for AI-assisted reviews. This guide maps the [RAISE framework (April 2026)](https://osf.io/fwaud/overview) to **Nested Knowledge** workflows.
Use it while writing your protocol and methods. It doesn't certify a review as RAISE-compliant.
### Disclaimer
This guide is an independent, high-level interpretation of RAISE. We have no affiliation with, endorsement from, or formal relationship with RAISE or its authors.
Read the original RAISE publications before setting requirements or claiming alignment.
### RAISE Principles For Authors
RAISE places ultimate responsibility for review integrity on the authors, regardless of the AI tooling used:
1. **Ultimate Author Accountability**: Responsibility for the integrity, accuracy, and completeness of a review lies fully with the authors.
2. **Transparency in Methods and AI Use**: Document how AI tools were used across the review cycle, including prompts, configurations, and human oversight.
3. **Fit-for-Purpose Methods**: Align with PRISMA, Cochrane, and similar standards, and use only fit-for-purpose AI tools.
4. **Human Oversight**: Critical steps (study selection, data accuracy, interpretation) require active human judgement.
5. **Bias Awareness, Risk Management and Limitations**: Mitigate biases introduced by AI tools and communicate limitations clearly in both methods and findings.
### RAISE Use-Acceptability Categories
RAISE classifies AI use into five tiers, which appear throughout the stage-by-stage guidance below.
| Tier | Definition |
| ------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Acceptable for Use** | AI outputs may be used directly within the review workflow *so long as limitations and biases are acknowledged and accounted for*. |
| **Human Verification Required** | AI outputs must be checked by humans. The degree of checking varies by task but typically requires reading and amending in its entirety. |
| **In-Review Validation** | AI outputs may be used *without full verification* if and only if in-review validation finds AI outputs adequate (e.g. comparable to humans). |
| **Exploratory and Supplementary Use** | AI may develop ideas or provide a starting point; all outputs should be extensively refined by humans, or used solely as additional approaches (adding to, not replacing, existing processes). |
| **Not Acceptable for Use** | At present, AI outputs have such serious limitations that they should not be relied upon. |
***
### Document Your AI Use
Record these details in your protocol and final methods:
1. The review stage, task, and **Nested Knowledge** tool used.
2. The tool configuration, prompts, and human review process.
3. Your in-review validation method, results, and any actions taken.
4. Limitations, unresolved uncertainty, and changes to the planned workflow.
Use [Disclosure of AI Systems](/policies/policies/artificial-intelligence-policies/disclosure-of-ai-systems-in-nested-knowledge.md) to document each tool's data use and model information.
### RAISE Principles By Review Stage
| Stage | RAISE position | Nested Knowledge compliance |
| -------------------------- | ---------------------------------------------------------------------------------------------- | -------------------------------- |
| **Search** | Scoping purposes or as a supplement to traditional search. | Yes — supplemental input. |
| **Screening** | Use should be validated within the review. | Yes — validate within review. |
| **Data Extraction** | Outputs should be reviewed; context-specific evaluation should be present. | Yes — review or validate data. |
| **Critical Appraisal** | Supplement to human appraisal, validated within the review. High risk of hallucination. | Yes — verify the draft. |
| **Qualitative Synthesis** | Suggestions for coding should be validated by a human. Summarisation is not synthesis. | Yes — check claims and evidence. |
| **Quantitative Synthesis** | Not acceptable for synthesising across studies via LLMs. AI-generated code must be documented. | Yes — document parameters. |
| **Text Generation** | Best-suited for summarisation of individual elements within a study. | Yes — scrutinize generated text. |
### Mapping Nested Knowledge AI Tools To RAISE Standards
The sections below cover each stage in turn: the relevant RAISE recommendations, the corresponding manual process, and the NK AI tool plus the expert curation needed to align with RAISE.
#### Search
AI search tools (LLMs, vector matching) do not always indicate where studies were retrieved from or the comprehensiveness of the search, and some have been shown to return fewer than half of studies captured in a traditional search.
**RAISE recommends** AI search be used for scoping or as a supplement to a traditional search to identify missed studies, and that sensitivity of the AI tool be considered.
| Manual Process | NK AI Tool & Expert Curation | RAISE Guidance |
| ---------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | --------------------------------- |
| Drafting full Boolean strings based on a Research Question | AI: Smart Search — a validated, iterative agentic workflow for search strategy development.
Expert: Fully scrutinise or treat as supplemental.
| Exploratory and Supplementary Use |
#### Screening
RAISE notes that prioritisation-screening stopping criteria are *"largely overconfident and fail to prevent missing relevant records,"* and that safer supervised approaches that maximise recall reduce time savings. LLM screening performance depends on prompt quality and example classifications.
**RAISE recommends** that ML and AI use in screening be validated within the review, that LLM usage for complex screening include structured examples or training, and that prioritised screening not be used without noting its limitations.
| Manual Process | NK AI Tool & Expert Curation | RAISE Guidance |
| ----------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------- |
| Screening at Abstract and Full Text stages (Dual or Single) | AI: Smart Screener answers criteria in Criteria-Based Screening. Robot Screener can fill one reviewer seat in Dual Screening.
Expert: In Dual Screening, retain a second human reviewer and a human adjudicator. Verify outputs or validate them within the review.
| In-Review Validation |
#### Tagging (Data Extraction)
RAISE considers data extraction an area where present tools can perform to an acceptable level. Rule-based algorithms have accuracy concerns due to terminology variation; ML can be more comprehensive but is dependent on the training corpus.
**RAISE recommends** hybrid use of rule-based and ML approaches (e.g. rule-based to identify candidate entities, then ML to filter), human review of LLM outputs for hallucinations and missing data, and context-specific evaluation when applying any AI extraction tool to a new domain (a *Study Within a Review*).
| Manual Process | NK AI Tool & Expert Curation | RAISE Guidance |
| ------------------------------------------------------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------- |
| Expert extraction of all qualitative and quantitative values | AI: Core Smart Tags extract a fixed hierarchy. Adaptive Smart Tags extract against your configured questions, including tables and figures in High Fidelity mode.
Expert: Verify outputs or validate them within the review before relying on them.
| In-Review Validation |
#### Critical Appraisal And Certainty Of Evidence
Automation is challenging due to low inter-rater reliability, which makes gold-standard training data hard to assemble. ML tied to specific tools or ensemble approaches have shown success; LLM prompting with detailed instructions is initially promising. GRADE-applying tools are still in development.
**RAISE recommends** LLM prompts include detailed instruction (including handling of incomplete information and connotation-laden words), that LLMs remain a supplement to human-driven checking, and that use be validated within the review. *Hallucination risk is high — verify carefully.*
| Manual Process | NK AI Tool & Expert Curation | RAISE Guidance |
| --------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ----------------------------------------------------- |
| \[Dual or Verified] Expert appraisal using study-type-specific Risk of Bias tools | AI: Smart Critical Appraisal drafts answers in your configured appraisal tool.
Expert: Verify outputs or validate them within the review. Check incomplete evidence and unsupported claims carefully.
| In-Review Validation — **High Risk of Hallucination** |
#### General Text Generation
Summarising information across multiple studies using AI is not recommended. Generative AI is best used for generating templates from human instructions as a starting point, or for summarising simple elements within a single study.
**RAISE recommends** AI not be used for interpretation of results or summarisation across studies. Best-suited current uses: summarisation of limited individual elements (e.g. interventions), plain-language summaries of human syntheses, and translation.
| Manual Process | NK AI Tool & Expert Curation | RAISE Guidance |
| ------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------- |
| Interpret and summarise or synthesise overall results and findings | AI: Smart Abstract and Synthesis Chat can help draft content from review data. Treat generated text as exploratory or supplemental.
Expert: Fully scrutinise it. Retain responsibility for interpretation and conclusions.
| Exploratory and Supplementary Use |
#### Qualitative Synthesis
RAISE draws a sharp distinction between **summarisation** (which LLMs can do) and **synthesis** (which they cannot): synthesis requires considering whether studies can validly be combined and testing the robustness of an analysis, none of which an LLM does when summarising text.
**RAISE recommends** all LLM suggestions for qualitative coding be validated by a human, and that LLMs only support qualitative coding — synthesis must remain human-centred.
| Manual Process | NK AI Tool & Expert Curation | RAISE Guidance |
| ----------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------- |
| Concept-by-concept summarisation of specific qualitative elements | AI: Smart Insights generates claims linked to studies and evidence in your nest.
Expert: Check each claim, source evidence, and interpretation before publication.
| In-Review Validation |
#### Quantitative Synthesis
Rule-based platforms can provide automated meta-analysis when statistics are available, including "live" updates of existing analyses. LLMs can generate analysis code, but RAISE states they are *"not acceptable for use"* for quantitative synthesis across studies.
**RAISE recommends** that LLMs not be used to synthesise results across studies, that statistical transformations be documented, that the reviewer have the analytical knowledge to review AI-generated code, and that LLM prompts for meta-analysis include example code. The quality of imported data should be evaluated before use.
| Manual Process | NK AI Tool & Expert Curation | RAISE Guidance |
| ------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | --------------------------------------------------- |
| Code-based network meta-analysis using standard statistical package | AI: Smart MA Extraction supports quantitative data extraction. Review it under the extraction requirements above. Quantitative Synthesis uses rule-based analysis.
Expert: Review the imported data, statistical parameters, and outputs. Document transformations and analytical choices.
| Acceptable for Use; Document Statistical Parameters |
***
**In summary:** Plan and record human review at every AI-assisted stage. Use in-review validation where RAISE requires it. Don't present AI outputs as final decisions or final interpretations.
***
### Validation Evidence
RAISE requires in-review validation at Screening, Extraction, Critical Appraisal, and Qualitative Synthesis. Plan that validation for your review context. Published studies don't replace your protocol-defined checks.
See [Validation studies](/ai-transparency/ai-in-nested-knowledge/validation-studies.md) for cited internal and independent evaluations.
**Cochrane CESAR Platform Study (March 2026).** Nested Knowledge was selected, alongside Laser AI, as one of two AI tools from a pool of 48 submissions to participate in Cochrane's [CESAR platform study](https://www.cochrane.org/about-us/news/cochrane-announces-selected-ai-tools-innovative-platform-study) evaluating AI tools for evidence synthesis. The selection process was [aligned with RAISE principles](https://www.cochrane.org/about-us/news/how-did-cochrane-select-ai-tools-evaluate-our-platform-study). Cochrane has been clear that selection is not a formal endorsement; pilot testing with Cochrane review author teams is underway, with interim analyses expected mid-2026
### FAQs
Does this guide certify my review as RAISE-compliant?
No. This guide supports your planning and reporting. Review the original RAISE framework for requirements.
Can an automated reviewer make the final screening decision?
No. In **Dual Screening**, automated reviewers require a human co-reviewer and human adjudicator.
Do published validation studies replace in-review validation?
No. Use published evidence to inform your plan. Validate the tool in your review context when RAISE requires it.
### Important Links
---
# 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/best-practices/compliance-guides/raise-compliance-guide.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.