Health sciences librarians are essential collaborators in the design and delivery of evidence syntheses. Earlier competency frameworks were developed with systematic reviews as the primary focus; however, evidence synthesis in the health sciences now includes scoping, rapid, realist, integrative, and mixed-method reviews. At the same time, the growing use of specialized technologies—such as AI-assisted search tools, automated screening platforms, and workflow management systems—has introduced new areas of required expertise.

This project updates the competency framework from Townsend et al. (2017) for health sciences librarians engaged in evidence synthesis. Using a narrative literature review approach, we synthesized research, guidance documents, and practice-based reports describing librarian roles and activities across review types. The analysis identifies competencies from the original framework that remain essential, including database expertise, rigorous search strategy development, and leadership in promoting transparency and reproducibility. It also introduces expanded competencies reflecting current practice, such as methodological literacy across diverse review approaches; instructional and mentorship responsibilities for learners and research teams; and the strategic and ethical use of technologies supporting searching, screening, data management, and dissemination.

The updated framework offers a contemporary, flexible set of competencies to guide professional development, inform curriculum design, and support institutional recognition of librarian expertise in evidence synthesis.

Keeping current on emerging AI tools for evidence synthesis can be a challenge for librarians who support knowledge synthesis projects like systematic, scoping, and other types of reviews. These tools are rapidly evolving and are increasingly being integrated into users' review processes. However, many AI tools for evidence synthesis exist behind paywalls with limited free trials and opportunities for librarians to fully explore all the features offered by the tool. This can greatly limit librarians' knowledge about how they might be used by a research team conducting a knowledge synthesis project.

This presentation is a case study that will showcase an approach that was employed by health sciences librarians at the University of Alberta for exploring and learning about the AI tool, Elicit Systematic Review. The process used was an informal one but still provided promising insights into the strengths and limitations of this AI tool. Librarians were able to develop evidence-based recommendations to provide practical guidance to researchers who are using this tool.