In this post, you’ll learn how Vanguard built their Virtual Analyst solution by focusing on eight guiding principles of AI-ready data, the AWS services that powered their implementation, and the measurable business outcomes they achieved.

Vanguard’s analysts and business stakeholders sought faster, more direct access to financial data for decision-making. The existing workflow required SQL expertise and data team support, with typical requests taking several days to fulfill. The data infrastructure required semantic context and metadata management to enable AI-powered tools to generate accurate, business-relevant insights.

As the Virtual Analyst project progressed, the team discovered that building effective conversational AI wasn’t a machine learning challenge—it was a data architecture challenge. The most sophisticated foundation models require proper data foundations to deliver reliable results. This realization led to a fundamental shift in approach: instead of focusing solely on AI capabilities, Vanguard needed to build what they termed AI-ready data.

Building Virtual Analyst requires something many organizations struggle with: getting traditionally siloed teams to work together. Vanguard brought together data engineers, business analysts, compliance officers, security teams, and business stakeholders. Each team brought critical expertise: