Wikatoni: An Agentic AI System for Energy Engineering Workflows
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.
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}
}
EUVIMED