Complex research tasks do not fit into a single prompt: they need tools, intermediate checks and an inspectable sequence of steps. These workshop materials introduce agentic AI as a workflow for digital humanities and archival research. They connect an Oxford research stay, CLARIN collaboration and practical work with NATO archival documents.
Agentic AI becomes useful when a task requires more than one prompt: collecting documents, checking intermediate results, calling tools and keeping a trace of decisions. The workshop material introduces these workflows in the context of digital humanities, where source provenance and the ability to inspect each step matter as much as the final answer.
The examples connect an Oxford research stay and CLARIN collaboration with NATO Archives work involving Lauren Sukin, Professorial Fellow at Nuffield College, and Michal Smetana, Visiting Fellow at All Souls College and Associate Professor at Charles University. The same research trip continued at the HTRes 2026 workshop at LREC 2026, focused on Holocaust testimonies as language resources.
Links
- Lecture notes: Detailed workshop notes on agentic workflows and archival research.
- Agentic AI Introduction slides: Introductory slide deck on AI agents and research tools.
- HTRes2026 proceedings: Proceedings of the LREC 2026 workshop on Holocaust testimonies as language resources.
- Lauren Sukin: John G. Winant Associate Professor and Professorial Fellow at Nuffield College, University of Oxford.
- Michal Smetana: Visiting Fellow at All Souls College, University of Oxford, and Associate Professor at Charles University.