A Virtual Member of a Community of Practice for the Society of Petroleum Engineers: From Prototype to Deployment
Source
John Boden, Joshua Eckroth, Dayne Freitag, Skyler Gipson, Johnathan Keefe, Karen Myers, Eric Schoen, Pedro Sequeira, Reid Smith, Michael Wessel
Author
John Boden, Joshua Eckroth, Dayne Freitag, Skyler Gipson, Johnathan Keefe, Karen Myers, Eric Schoen, Pedro Sequeira, Reid Smith, Michael Wessel
Date
Terms in this piece · Glossary
RAG — Retrieval-augmented generation — fetching relevant documents first and pasting them into the model's context so it answers from your data instead of memory.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
Why it matters
A rare prototype-to-deployment account of a knowledge AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → measured against a strong RAGRetrieval-augmented generation — fetching relevant documents first and pasting them into the model's context so it answers from your data instead of memory.Full definition → baseline with 75 real professionals, including which weaknesses forced rework: multi-document retrieval, answer validation, and targeted proactive dissemination.
articleResearch Assistant: AstraZeneca's Agentic System for R&DPiotr Grabowski, Mohamed Alameen, Jorge Bretones, Sabina Cardell, Miguel Carmona, Gavin Edwards, Ben Grainger, Sameh Hassan, Erik Jansson, Artur Kuziakhmetov, Albert Maristany, Hebatallah Mohamed, Andriy Nikolov, Sebastian Nilsson, Mark O'Donoghue, James Pacileo, Ashiq Sultan, Alex Voegele, Michael Ughetto
articleBC-Bench: Evaluating Agentic Engineering in a Domain-Specific Language for ERPHaoran Sun, Klaus Marius Hansen
articleAI Evaluation Should Work With HumansJan Kulveit, Gavin Leech, Tom\'a\v{s} Gaven\v{c}iak, Raymond Douglas