The digital platform serves as the central infrastructure for all research activities of the SFB. Aligned with the SFB’s two main objectives – the elucidation of Neo-Latin’s role in the early modern world and the integration of Neo-Latin Studies into early modern research as a whole – it fulfills two distinct functions.

Internally, it manages the data foundation for all eight sub-projects, integrating their texts and data while providing tools for analysis; this guarantees the coherence of the SFB’s research program. Externally, it serves as an interface with the wider academic community. By expanding its contents systematically for maximal usefulness, it positions itself as the go-to reference for all scholars interested in the early modern world, regardless of their proficiency in Latin. These goals are achieved through four core elements:

1. Text Corpus

At the core of the platform is the construction of the largest corpus of digitized and machine-readable Neo-Latin texts. Utilizing the AI-powered platform Transkribus, the project assembles a machine-readable document collection selected according to pragmatic criteria of scholarly relevance. Once fully implemented, the corpus will support advanced full-text searches, proximity queries, and automated named-entity recognition, enabling the exploration of themes, concepts, persons, and places across a wide range of contexts.

2. Structured Database

The corpus is complemented by a structured database of persons, works, translations, manuscripts, and printed editions, as well as relevant secondary literature. Implemented using Wikimedia technologies, it links to external resources such as Wikidata, Wikipedia, and other Neo-Latin digital projects. This component facilitates the analysis of textual production networks and the study of cultural and linguistic mediation across regions and periods.

3. AI Chatbot

The platform integrates an AI-powered chatbot based on Large Language Models (LLMs). Grounded in the curated data of the project’s database and text corpus, the chatbot provides translations from Latin and offers contextual information on texts, authors, and concepts. By lowering the barrier for engaging with Neo-Latin sources, this tool supports exploratory research and pedagogical applications while remaining transparent about the limitations of machine-generated output.

4. Curated Resources

Finally, a selected collection of digital tools and resources serves the broader research field. Unlike static lists, this collection is strictly curated and continuously updated to ensure long-term reliability. It includes the rectification of addresses and the removal of obsolete data. The collection includes, but is not limited to:

• Machine-readable Latin text corpora, such as the Corpus Corporum, CAMENA, Poeti d’Italia in lingua latina, CroALa, The Library of Humanistic Texts.
• Modern tools, such as dictionaries (e.g., Ramminger’s Neulateinische Wortliste), encyclopaedias (e.g., Brill’s English online version of Jäger et al. 2005–12), national biographies (Dizionario Biografico degli Italiani, Deutsche Biographie), bibliographic catalogues (e.g., USTC; VD16, 17, 18), indexes of names (e.g., Gemeinsame Normdatei) and abbreviations (Winiarczyk 1995), and image sources (Warburg Institute Iconographic Database).
• Early modern resources (as scans or, when available, machine-readable transcripts), which often reflect the state of knowledge and the mindset of their own time more precisely and in greater detail than modern ones, e.g., dictionaries, encyclopaedias, bibliographies, and historiae litterariae (cf. the thesaurus section of CAMENA).