# Databricks proposes shared infrastructure to curb AI agent sprawl

> Original title: Every new agent can become another integration, policy set and observability stack to maintain.

- Source: Databricks
- Published: 2026-10-22T18:30:04.000Z
- Bad Influence: https://badinfluence.news/items/bfiplheoo6umjdov3or8r0d9w
- Original: https://x.com/databricks/status/2113337107343138830

## Summary

Databricks says that as AI agents act across data, models, tools and business systems, each new agent adds integrations, policies and observability stacks to maintain. It proposes shared infrastructure built on Agent Bricks for building, governing and optimizing agent fleets, Omnigent for composing agents across harnesses, and Unity Gateway for centralized access, cost controls and observability.

## Post

Every new agent can become another integration, policy set and observability stack to maintain.

As agents take actions across data, models, tools and business systems, that fragmentation gets expensive fast. The better pattern is shared infrastructure for choice, context and control:

1️⃣ Agent Bricks for building, governing and optimizing agent fleets
2️⃣ Omnigent for composing agents across harnesses
3️⃣ Unity Gateway for centralized access, cost controls and observability

https://www.databricks.com/blog/how-scale-agentic-applications-without-creating-ai-sprawl?utm_source=twitter&utm_medium=organic-social

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHVQU5l-WwAAiqiM.png&mode=thumb&exp=1793836800&sig=726d26c7a13da416)