Abu Dhabi: ADNOC and AIQ announced today the successful proof-of-concept trial of ENERGYai, the world's first-of-its-kind agentic artificial intelligence (AI) solution tailored for the energy sector. ENERGYai integrates a 70-billion-parameter large language model (LLM) with over 50 years of ADNOC's knowledge and petabytes of its proprietary data to drive optimization and efficiency across the company's operations.
According to Emirates News Agency, the 90-day proof-of-concept trial demonstrated that ENERGYai's agentic AI-AI 'agents' trained in specific tasks across the energy value chain-can deliver significant improvements in the pace and accuracy of upstream exploration through rapid, precise, and detailed seismic survey analysis. It also provided relevant, actionable insights to support production optimization at ADNOC's existing wells. ENERGYai delivered its insights in intuitive, natural language, enabling engineers to interact with it effectively and easily.
The results of the trial delivered promising real-world outcomes, including a 70 percent improvement in accuracy in major seismic interpretation aspects and significant enhancements in advanced reservoir monitoring and anomaly detection. Musabbeh Al Kaabi, ADNOC Upstream CEO, stated that the successful completion of this proof of concept for ENERGYai has shown extremely promising results and confirmed the potential of the solution to be a powerhouse for value creation and sustainable energy production. He added that ENERGYai will leverage petabytes of data to empower ADNOC's workforce and future-proof the company in its quest to become the world's most AI-enabled energy company.
The ENERGYai trial also showed promising results in enhancing data quality by vastly improving the reliability and usability of operational data inputs through detecting errors, standardizing formats, and enriching datasets. Magzhan Kenesbai, Acting Managing Director of AIQ, emphasized that this milestone was made possible through the alignment of ADNOC subject matter experts, the expertise of over 100 specialists, and the establishment of secure AI infrastructure, laying the foundation for greater accomplishments in future phases.
Following the successful proof of concept, the first operational, scalable version of ENERGYai is expected to be completed in the first half of 2025. This version will include five fully operational AI agents covering tasks within subsurface operations and will be test-deployed across several upstream assets, with plans to scale its application to thousands of additional wells.