Enterprise services · AI Implementation
Building the data layer before anyone ships an agent.
The situation
An enterprise services organization had just finished a one-day AI accelerator with a major cloud provider. The accelerator produced a strong list of use cases. Teams were excited. Leadership wanted to ship. But the data underneath was at 1.5 out of 5 on a governance maturity scale. The agents the use cases described had nowhere reliable to read from.
What we found
The proposed agents needed reliable sources and clear access rules. The team also needed a record of which agents existed, what each could do, and who was responsible for it. Those requirements shaped the work before model selection.
What we built
A data architecture roadmap that named the foundation layer explicitly: a governed data platform with column-level access controls, a Model Context Protocol surface over it so agents can query through one consistent interface, and an agent registry that records every deployed agent with its scope, owner, and data permissions.
The architecture made the data sources and permissions explicit, giving the team a consistent basis for developing and reviewing agents.
What changed
The team separated use cases that could proceed against the data layer from those needing three quarters of preparation. That gave each project a scope and a schedule. The frontline teams who actually do the work were brought into the conversation about which agents got built first, because they were the ones who would be auditing the outputs.