Online Live Streaming Course

June 23 to 27, 2025

Duration : 20 hours

Level : Intermediate – Advanced

WHO SHOULD ATTEND:  This course is for drilling engineers and operations managers looking to apply analytical AI modeling and large language models in drilling applications—from operations management to well construction design. Coding proficiency is required to grasp the advanced concepts and implement effective solutions.

COURSE CONTENT AND OBJECTIVES:

This course offers a well-rounded blend of traditional analytical AI and advanced generative AI (GenAI) and large language model (LLM) concepts. It covers a wide range of topics, from regression analysis to advanced applications in search, summarization, content, and code generation. Attendees will explore analytical AI models for operations management and well construction modeling, alongside techniques like embeddings, semantic search, RAG (Retrieval-Augmented Generation), agents, and prompting methods such as zero, one, and few-shot, chain of thought, and self-criticism. The curriculum focuses on practical applications in drilling data analytics, covering a wide range of concepts from regression analysis to search, summarization, content, and code generation. Designed for drilling engineers, this course lays a strong foundation in both traditional and cutting-edge AI, equipping participants with a comprehensive knowledge base for drilling data analytics.

Course content includes:

• Introduction to AI in drilling: AI’s role in optimizing well construction and operations, focusing on regression analysis for performance prediction and time series analysis for event detection in drilling data.
• Generative AI and LLMs: Overview of LLMs and their applications in summarizing well logs, generating insights from operational data, and how RAG (Retrieval-Augmented Generation) can enhance these tasks.
• Embeddings and semantic search: Using embeddings to query and retrieve relevant drilling data for decision-making, with a practical session on semantic search for wellbore data.
• Prompting techniques: Exploring zero-shot, one-shot, and few-shot learning, along with chain-of-thought and self-criticism prompting methods to improve model outputs. Practical exercises on applying these techniques to real-world drilling data.
• AI agents in drilling: Introduction to autonomous decision-making using AI agents and their integration in drilling optimization.
• Practical applications: Developing AI tools for data search, summarization, and content generation for well logs, as well as generating code for data processing.