AES accelerates renewable energy adoption with Claude on Google Cloud

Overview

AES, a global energy company, built a multi-agent AI system using Claude on Google Cloud to automate internal safety audits of its renewable energy assets. The system uses document processing agents, task breakdown agents, and report generation agents to process hundreds of pages of safety documentation, evaluate compliance, and produce audit reports. Audit reports that previously took up to two weeks to complete (across roughly 1,550 internal audits annually) can now be generated in about an hour, a 99% reduction in time, alongside a 10-20% improvement in audit accuracy and a 99% reduction in audit costs.

The challenge

As AES transitioned to renewable energy, it had to manage a vastly more complex network of power-generating assets -- for example needing 75 wind turbines (1.5 megawatts each) to match the output of one large traditional turbine. AES conducts about 1,550 internal safety audits annually, typically performed by employees whose primary roles are not auditing, and these audits could take up to two weeks to complete, becoming an unsustainable drain on time and resources.

The solution

AES developed an AI-powered auditing system using Claude on Google Cloud, consisting of three layers of AI agents: document processing agents that analyze audit documents and create tasks, task breakdown agents that simplify complex audit tasks, and report generation agents that compile results into final audit reports. The multi-agent system processes hundreds of pages of safety documentation and evaluates compliance.

Reported business value

Audit reports that took two weeks to complete can now be generated in about an hour, a 99% reduction in audit time. AES has also seen a 10-20% improvement in audit accuracy, and audit costs have been reduced by 99%.