Scaling Talent Mobility With Governed AI and Agent Bricks

Overview

Guild built Catalog Atlas, an enterprise-grade domain-specific agent on Databricks AI and Agent Bricks, to serve as the authoritative source of information on its learning catalog of hundreds of providers and programs. The solution cut query times by more than 80% during development, reclaimed 450 hours of productivity annually worth $33,750, and reduced manual QA checks by over 90% via automated AI judges.

The challenge

As Guild grew, critical knowledge about its extensive catalog of education and skilling programs was spread across multiple platforms, from dashboards and spreadsheets to internal wikis and Slack threads. Before Catalog Atlas, accessing information could take hours or require waiting upwards of 24 hours for a Slack response, while team members were constantly interrupted to answer the same questions.

The solution

Guild turned to the Databricks Data + AI Platform to unify its knowledge, govern access, and build Catalog Atlas, a custom agent that puts trusted, context-aware information at employees' fingertips. Built on Databricks, Catalog Atlas unified structured and unstructured data into Delta tables, Volumes, and Vector Stores, all governed by Unity Catalog, with MLflow evaluations creating a continuous improvement loop and Agent Bricks used for early prototyping.

Reported business value

Automating catalog-related queries saves Guild an estimated 450 hours per year, generating $33,750 in annual value that can be redirected toward higher-impact projects. This agility helped Guild cut query times by more than 80% during development, and MLflow evaluations reduced manual QA checks by over 90% through the use of automated AI judges.