• Share this post Keep up with us Summary Build and deploy governed, serverless AI agents without managing infrastructureGo from prototype to production faster with templates, evaluation, and CI/CD workflowsShip context-aware agents with built-in memory, data connectivity, and unified governance Build and deploy governed, serverless AI agents without managing infrastructure Go from prototype to production faster with templates, evaluation, and CI/CD workflows Ship context-aware agents with built-in memory, data connectivity, and unified governance Agent BricksCustom Agents, formerly Agent Framework, is now available on Databricks. • Custom Agents allows developers to use their existing tools and workflows to rapidly build, test, and deploy production-quality AI agents as fully managed Databricks Apps. • Developers don’t need to re-architect code or manage infrastructure. • Teams can build agents locally, use AI coding tools, and iterate quickly on agent quality with tight feedback loops before deploying. • Prebuilt agentskills,templatesand integrated evaluation reduce setup work and help developers move from prototype to production faster. • Custom Agents integrate naturally into existing development workflows, including CI/CD pipelines, so teams can continuously test, refine, and ship improvements without re-architecting deployments.

Article Summaries:

  • Databricks has released Custom Agents, a new feature that lets developers build, test, and deploy AI agents as fully managed Databricks Apps without re‑architecting code or managing infrastructure. The tool supports local development, AI coding assistance, and rapid iteration with prebuilt skills, templates, and evaluation tools, enabling a smoother transition from prototype to production. Custom Agents integrate with existing CI/CD pipelines, allow use of preferred models and frameworks, and run on serverless compute with built‑in security and governance. Built‑in memory via Lakebase preserves agent state and conversation history, while direct connections to enterprise data reduce integration effort. The feature is available now, with documentation to help teams get started.

Sources: