ADNOC and AIQ successfully complete trial phase of agentic AI solution

ADNOC and AIQ announced on Thursday the successful proof-of-concept trial of ENERGY^ai, the world’s first-of-its-kind agentic artificial intelligence (AI) solution tailored for the energy sector. ENERGY^ai 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, the company said in a statement.

The 90-day proof-of-concept trial demonstrated that ENERGY^ai’s agentic AI – AI ‘agents’ that are 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, alongside relevant, actionable insights to support production optimization at ADNOC’s existing wells. ENERGY^ai was able to deliver its insights in intuitive natural language, enabling engineers to interact with it effectively and easily.

Promising real-world results

The results of the trial delivered promising real-world results, including a 70% improvement in accuracy in major seismic interpretation aspects and significant improvements in advanced reservoir monitoring and anomaly detection, ADNOC said.

“The successful completion of this proof of concept for ENERGY^ai has shown extremely promising results, and has confirmed the potential of the solution to be a powerhouse for value creation and sustainable energy production,” said Musabbeh Al Kaabi, ADNOC Upstream CEO.

“Building on this initial achievement, ENERGY^ai will leverage petabytes of data to better empower our people and future-proof ADNOC, as we work to become the world’s most AI-enabled energy company,” he added.

The ENERGY^ai trial also showed promising results in enhancing data quality, as it vastly improved the reliability and usability of operational data inputs by detecting errors, standardizing formats and enriching datasets.

Robust AI infrastructure

Magzhan Kenesbai, Acting Managing Director of AIQ, said: “This milestone was made possible through close alignment between ADNOC subject matter experts, the expertise of 100+ specialists, and the establishment of robust and secure AI infrastructure. These factors lay the foundation for even greater accomplishments in the forthcoming phases.”

Following the successful proof of concept, the first operational, scalable version of ENERGY^ai is expected to be completed in H1 2025. This version will include five fully operational AI agents covering tasks within subsurface operations and will be test-deployed across a number of upstream assets, with plans to scale its application to thousands of additional wells.