EUVIMEDEUVIMED entdecken
Crossref

Wikatoni: An Agentic AI System for Energy Engineering Workflows

Sampath Rajapaksha, Nirmalie Wiratunga, Ikechukwu Nkisi-Orji, Tim Clarke, Fraser Kerr

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (48) · 41667-41669

DOI: 10.1609/aaai.v40i48.42375 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Sampath Rajapaksha und 4 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Capturing expertise and enabling efficient information retrieval are critical in the energy sector, where high staff turnover can lead to significant knowledge loss. Retrieval Augmented Generation (RAG) offers a solution by grounding Large Language Model (LLM) outputs in documented sources, but its effectiveness is limited by reliance on general-purpose embeddings. We present Wikatoni, an agentic AI system for energy engineering workflows that integrates a novel domain-specific embedding model. Wikatoni combines fine-tuned embeddings with agentic RAG, metadata filtering, and hybrid retrieval to improve document search, automated reporting, and workflow efficiency. Evaluation on internal enterprise offshore energy data shows that the domain-adapted embedding improves recall by 10%, and Wikatoni agentic RAG further increases answer accuracy by 14% compared to vanilla RAG with the base embedding model, achieving the best overall performance in context recall, faithfulness, and answer accuracy.

Zitieren

APA

Rajapaksha, S., Wiratunga, N., Nkisi-Orji, I., Clarke, T., & Kerr, F. (2026). Wikatoni: An Agentic AI System for Energy Engineering Workflows. Proceedings of the AAAI Conference on Artificial Intelligence, 40(48), 41667-41669. https://doi.org/10.1609/aaai.v40i48.42375

Vancouver

Rajapaksha S, Wiratunga N, Nkisi-Orji I, Clarke T, Kerr F. Wikatoni: An Agentic AI System for Energy Engineering Workflows. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(48):41667-41669. doi:10.1609/aaai.v40i48.42375

BibTeX
@article{Rajapaksha2026,
  author = {Rajapaksha, Sampath and Wiratunga, Nirmalie and Nkisi-Orji, Ikechukwu and Clarke, Tim and Kerr, Fraser},
  title = {Wikatoni: An Agentic AI System for Energy Engineering Workflows},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {48},
  pages = {41667--41669},
  doi = {10.1609/aaai.v40i48.42375}
}
Kostenlos starten →