agent bricks custom agentFormerly Agent Framework, now available on Databricks. Custom agents allow developers to use their existing tools and workflows to rapidly create, test, and deploy production-quality AI agents as fully managed Databricks apps. Developers do not need to re-architect code or manage infrastructure.
Teams can build agents locally, use AI coding tools, and increasingly focus on agent quality with tight feedback loops before deployment. preformed agent Skill, Templates And integrated evaluation reduces setup work and helps developers move faster from prototype to production.
Custom agents integrate naturally into existing development workflows, including CI/CD pipelines, so teams can continuously test, refine, and ship improvements without having to reorganize deployments. Without rewriting code or adopting vendor-specific environments, developers can continue to use their favorite models, frameworks, and tools.
When ready for deployment, agents run as Databricks apps on serverless compute with built-in security and governance. This provides a consistent production environment without having to manage infrastructure or coordinate handoffs to platform teams.
Built-in memory powered by Lakebase provides developers a production-grade way to store and reuse agent state and conversation history, so agents remain context-aware across stages and sessions without additional infrastructure. Agents connect directly to enterprise data and systems with consistent governance across data, models, and agent operations, reducing custom integration work and helping teams deploy reliable, domain-aware agents faster.
Custom Agent is now available. check out Documentation To start.
