Building Enterprise-Ready Agents using Agent Bricks

While AI agent development is rapidly evolving in the consumer space, enterprise AI faces unique hurdles such as data privacy, governance, and the "agent sprawl" challenge. This session introduces Agent Bricks, a unified platform designed to cure these challenges by integrating governance directly through Unity Catalog and observability via MLflow. The presentation details how to move beyond low-quality reasoning on isolated enterprise data to building sophisticated systems, including knowledge assistants for unstructured data and multi-agent supervisors for complex reasoning tasks. Key Takeaways: - State of Enterprise AI: 78% of companies now adopt a multi-model strategy to stay ahead of rapid model releases. - The Impact of Governance: Organizations investing in AI governance and security are shipping 12 times more projects into production. - Curing Agent Sprawl: Addressing "agent sprawl" through contextual reasoning and unified governance to prevent issues like silent degradation and hallucinated metrics. - Agent Bricks Capabilities: Leveraging Agent Bricks for automated dashboard authoring, conversational analytics with Genie, and multi-agent coordination.