Faculty AI Upskilling

Through our Upskilling Workshops — hands-on sessions for faculty, researchers, and graduate students — the AI Research Initiative at UVA offers targeted, practical training for those wanting to extend their research with AI.

The 2026 Summer Workshop Series has concluded. Below you can browse the full lineup and request session materials.

Stay tuned for more about the Fall Upskilling series, coming soon!

Agentic Workflows in Practice

Reza Mousavi (McIntire School of Commerce)

June 5, 2026

Overview: How AI agents support complex research workflows, and when they offer advantages over traditional browser-based tools. Hour 1 covers the foundations of agentic workflows — core concepts, capabilities, and design logic. Hour 2 puts them into practice with state-of-the-art tools to search, summarize, compare, and synthesize information.

Keywords: AI agents; agentic workflows; research automation; synthesis tools

Your First API Call: Scaling AI on UVA HPC

Joshua Baller (Research Computing)

June 10, 2026

Overview: A hands-on introduction to calling LLM APIs from a Jupyter notebook on UVA's High Performance Computing (HPC) systems, including how to scale workflows beyond the browser into reusable or batch processes. For faculty and researchers with basic Python experience who want to build scalable, programmatic AI workflows.

Keywords: LLM APIs; HPC; Jupyter; Python; batch processing

Smarter Literature Reviews with AI-Powered Tools

Stephen Turner (School of Data Science)

June 17-18, 2026

Overview: Practical workflows for faster, more effective literature reviews, using Zotero alongside AI tools like Consensus and Inciteful to discover, organize, and synthesize research. No prior experience with the tools required.

Keywords: literature review; Zotero; Consensus; Inciteful; research discovery

Converting Large-Scale Text into Analyzable Data

Ben Castleman (Batten School) & Kathryn Linehan (Research Computing)

June 23, 2026

Overview: A comparison of expert NLP and AI-assisted approaches for transforming large text datasets — essays, surveys, interviews, policy documents, clinical notes — into structured, analyzable data. For researchers working with large text datasets.

Keywords: NLP; text analysis; unstructured data; survey/interview data

Vibe Coding: Rapid Research Prototyping with AI

Jingjing Li (McIntire School of Commerce)

July 15-16, 2026

Overview: Using AI coding assistants (e.g., Claude Code) to quickly prototype research tools, data pipelines, and experimental workflows without building full systems from scratch. "Vibe coding" is an iterative, conversational approach to developing code with AI — useful for testing ideas, building proof-of-concept tools, and exploring new research methods.

Keywords: vibe coding; Claude Code; prototyping; AI coding assistants; data pipelines

Designing an AI-Powered Research Pipeline

Matthew Trowbridge (School of Medicine)

July 20 & August 10, 2026

Overview: Building an end-to-end, AI-powered research pipeline — connecting data collection, processing, and analysis steps into a repeatable workflow.

Keywords: research pipeline; workflow automation; end-to-end AI; reproducible workflows

Research Synthesis & Discovery: AI-Augmented Zotero

Jeremy Boggs, Chris Ruotolo, Maggie Nunley, Rebecca Coleman (UVA Libraries)

July 22, 2026

Overview: An extended, hands-on session on building an AI-augmented Zotero workflow for research synthesis and discovery — organizing sources, surfacing connections, and accelerating the path from collection to insight.

Keywords: Zotero; research synthesis; reference management; source discovery

AI-Enhanced Literature Reviews: Tools & Guardrails

Maggie Nunley (UVA Library)

July 29, 2026

Overview: An advanced, in-person session on navigating the evolving landscape of AI research tools with rigor: strategic tool selection (Consensus, Elicit), mapping research landscapes and citation networks, integrating AI into established review practice, and applying guardrails for attribution, bias detection, and institutional compliance.

Keywords: literature review; Elicit; research integrity; bias detection; attribution

Making AI Work Legible: Transparency, Reproducibility, and Trust

Alex Gates (School of Data Science)

July 30, 2026

Overview: How to document and justify the use of AI in research so that workflows remain interpretable, reproducible, and credible. Covers where AI enters the research pipeline, common failure modes, and practical strategies for disclosure, validation, and communicating methods in papers and proposals.

Keywords: reproducibility; transparency; AI disclosure; research rigor; method reporting

Questions? 

Contact Jason Nabi