Skills SA has built a multi-agent AI workflow to help review how vocational education and training providers meet student support requirements, running largely on a Databricks stack. AI, data and integration lead Jarrad Taylor, speaking at the Databricks Data + AI Summit in San Francisco, said the initial use case assists assessors reviewing responses to an annual compliance process known as the Organisational Self Assessment (OSA), a 40-to-50 question form providers must complete annually to show they meet six Skills SA ‘student support standards’. Taylor said reviewing the self-assessments was manual, time-consuming, and challenging to ensure consistent assessment. Work on the multi-agent system started about 18 months ago; a supervisor agent orchestrates three other agents—an operational agent, an analysis agent, and a decision support agent—that assess completed OSA forms. Taylor described three layers of benefit: reducing time for assessors on routine activities, providing real-time visibility for operational staff into workflow statuses and trends, and helping Skills SA apply standards more consistently while maintaining a complete audit trail. He suggested the setup represents a reusable pattern applicable to other enterprise processes, with reuse inside Skills SA already on the cards.