{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T10:21:04Z","timestamp":1773829264694,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"48","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>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.<\/jats:p>","DOI":"10.1609\/aaai.v40i48.42375","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T07:59:23Z","timestamp":1773820763000},"page":"41667-41669","source":"Crossref","is-referenced-by-count":0,"title":["Wikatoni: An Agentic AI System for Energy Engineering Workflows"],"prefix":"10.1609","volume":"40","author":[{"given":"Sampath","family":"Rajapaksha","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nirmalie","family":"Wiratunga","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ikechukwu","family":"Nkisi-Orji","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tim","family":"Clarke","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fraser","family":"Kerr","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"9382","published-online":{"date-parts":[[2026,3,14]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/42375\/46336","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/42375\/46336","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T07:59:24Z","timestamp":1773820764000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/42375"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"48","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1609\/aaai.v40i48.42375","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,14]]}}}