Agent Bricks: The governed enterprise agent platform

Summary

Agent Bricks is presented as Databricks’ enterprise platform for building, deploying, and governing agents that operate on business data under real identities, permissions, and operational constraints. The platform combines multi-model and framework support, execution, routing, fallback, cost optimization, and unified governance through Unity Catalog and AI Gateway, including on-behalf-of token passing and observability across data, models, MCPs, and APIs. Its context layer uses metadata such as schemas, business definitions, lineage, permissions, and data-quality signals, while Genie Spaces, Document Intelligence, Knowledge Assistant, and Agent Mode address structured and unstructured business information. The announcement includes general availability for Document Intelligence, Custom Agents on Apps, and Supervisor Agent, plus AI Gateway guardrails, managed OAuth MCP Connectors, web search, and MLflow’s CLEARS evaluation framework; the post reports 70% higher accuracy than standard RAG and a 30% improvement in multi-step workflows.

Context

The post says enterprise agents are difficult to run in production because they must work with real business data, permissions, identities, policies, and operational systems. It also identifies model lock-in, credential exposure, insufficient business context, and limited observability as challenges that agent products often address only partially.

Approach / What changed

Agent Bricks unifies model access, execution, governance, and business context in one platform. Its capabilities include multi-model routing and fallback, Unity Catalog and AI Gateway governance, on-behalf-of identity propagation, MCP connectors, document and knowledge ingestion, agent orchestration, serverless agent applications, and MLflow-based quality evaluation.

Takeaways

• Custom Agents on Apps provides full lifecycle support, any model or framework, serverless compute, and native Lakebase integration for memory, conversation history, and state in long-running workflows.
• AI Gateway now governs MCP-connected tools as well as models and coding agents, with guardrails for PII exposure, unsafe content, prompt injection, data exfiltration, and hallucinations.
• The CLEARS framework in MLflow evaluates agent quality across correctness, latency, execution, adherence, relevance, and safety.

Related reading