Enterprise Knowledge Search · IT Operations Automation
Repsol wanted to help employees reinvent workflows, improve working models, and raise productivity in complex internal processes as part of its broader digitalization program.
Reported impact
Repsol reports that the platform helps teams create new collaborative environments, improve working models, and boost productivity while supporting relevant departmental processes with supervised multi-agent workflows.
Repsol built its own intelligent agent construction platform as a pilot for agent-based AI and multi-agent systems, developed in collaboration with Accenture for the Digitalization and Services department. The platform acts as an orchestration layer where teams can configure AI agents into workflows so the agents can self-organize, coordinate, and perform task groups tied to real departmental processes. To ground those agents in team-specific context, Repsol created large knowledge bases designed exclusively for the teams using the system. It also introduced an interface that adapts language models to a professional, collaborative environment so employees can work with and supervise agent teams rather than use isolated chat interactions. In production use, three teams deployed 22 AI agents, and more than 50 people collaborated with and supervised the agents over more than four months, making the platform a structured internal environment for workflow support and productivity improvement.
Team knowledge is organized into dedicated knowledge bases, the intelligent agent construction platform uses that context to configure AI agents into workflows, and employees interact with and supervise the agent teams through an interface that adapts language models to professional collaboration.
"It has also designed an innovative interface that adapts language models to a professional and collaborative environment."
"Since the launch of its Generative AI Competence Center more than two years ago, Repsol has positioned itself as a pioneer in the global energy sector in the use of generative AI, accumulating experiences and tangible results: more than 60 use cases in production, 22 of which have already been scaled up, and the training of more than 5,000 employees in generative AI or advanced prompting techniques."
"Subsequently, more than 50 people have been working collaboratively, supervising teams of AI agents, thus, achieving numerous efficiencies and improvements."
"The company has taken another step forward in its digitalization process by launching a platform for building intelligent agents that makes it easier for employees to reinvent workflows and improve their productivity."
"The pilot has been carried out in Repsol's Digitalization and Services department, which has more than 700 employees and where three teams with 22 AI agents have been deployed, providing support for more than four months in processes relevant to the area."
"The platform, an innovative pilot project developed in collaboration with Accenture, facilitates the configuration of artificial intelligence agents that are organized into workflows."
"Throughout the planning and development of the multi-agent system, Repsol has created large knowledge bases designed exclusively for teams to get support from the AI agents."
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 Jul 23, 2026 Telefónica Telefónica needs to evolve and maintain a very large API and microservices estate without slowing delivery, while keeping integrations understandable, compliant, secure and maintainable; it also wants to reduce manual… AI agent · generative AI In-house Sample Mar 30, 2026 Telefónica Germany Telefónica's network operations teams had to handle growing network complexity, massive alarm volumes, and incident analysis workflows that made root-cause identification and troubleshooting slower and harder for NOC… Network Operation Agent (NOA) · database · ticketing system 
Microsoft Sample Jun 6, 2024 Petrochemical Industries Company (PIC) In the petrochemical industry, staying ahead means leveraging cutting-edge technology. Microsoft 365 Copilot quickly gained the endorsement of various departments. Microsoft 365 · Microsoft Copilot for Microsoft 365 · Microsoft Teams 