Enterprise Knowledge Search
Rio Tinto wanted AI and advanced analytics solutions that help operating teams work more safely and efficiently, and it needed a fast way to support its Annual Planning Review workshop with better access to organizational knowledge.
Reported impact
Rio Tinto delivered an internal AI knowledge agent in three weeks, used it in the Annual Planning Review workshop, and reinforced senior leadership’s decision to incorporate AI into business strategies while supporting safer and more efficient operations.
Rio Tinto’s Data & Analytics team built and deployed an internal GPT-like knowledge agent for the company’s Annual Planning Review workshop. The implementation was led by a senior data scientist and used generative AI and large language models as the core reasoning layer for the assistant. Based on the source, the agent was created to help workshop participants access and use relevant knowledge more effectively during planning activities, while supporting the company’s broader objective of safer and more efficient operations. The work was delivered through cross-team collaboration and shipped in only three weeks, enabled by technical groundwork completed in prior months. The source does not name external vendors, hosting platforms, storage systems, or integrations, so the documented architecture is limited to the internal knowledge agent, the LLM-driven processing layer, and its use in the planning workshop context.
"The project’s success also reinforced the senior leadership team’s decision to incorporate AI into their business strategies"
"These solutions are designed to help our teams operate safely and efficiently"
"We leveraged cutting-edge technology such as Generative AI and Large Language Models (LLMs)"
"ensure timely delivery in only 3 weeks"
"leading the development of a Generative Pre-Trained Transformer (GPT) like knowledge agent for the Annual Planning Review workshop"
"my role involves developing and implementing AI and advanced analytics solutions"
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
In-house Sample Apr 22, 2026 ABB ABB wanted to give employees a safe, responsible way to use generative AI in daily work so they could improve productivity, explore ideas more effectively, and support ongoing learning and career development. Abby supports more than 15 large language models (LLMs) Abby In-house Sample May 28, 2024 Airbus Airbus needs faster, easier access to complex technical and manufacturing documentation across engineering, manufacturing, after-sales service, and other operations while meeting the aerospace sector's regulatory and… 600 use cases have been identified across Airbus in less than a year AI assistant for Standard Operating Instructions · base models · chatbot In-house Sample Feb 19, 2024 GEA Industrial operators using GEA equipment need to increase output while consuming less energy and generating less waste under changing process conditions, tighter environmental standards, and talent scarcity. GEA also… 50% connection rate of new IIoT-ready installations by the end of the year CattleEye · GEA BetterBot AI · GEA Cloud 