Databricks has introduced a suite of new tools designed to assist enterprises in scaling AI agents from pilot projects to full production phases. The tools are intended to provide organisations with greater confidence in deploying AI agents in high-value, mission-critical applications, while ensuring accuracy, governance, and ease of use.

The newly launched tools include the Mosaic AI Gateway, Genie Conversation API suite, Agent Evaluation Review App, and Batch AI. These tools are now available in Public Preview.

The Mosaic AI Gateway is designed to offer centralised governance for all AI models. It integrates and manages both open source and commercial AI models in a single platform. This tool aims to streamline the management of AI models, providing a unified approach to governance.

The Genie Conversational API suite is aimed at developers looking to embed natural language-based chatbots into custom-built applications or productivity tools. It supports integration with platforms such as Microsoft Teams, Sharepoint, and Slack, thereby enhancing communication capabilities within enterprise environments.

The Agent Evaluation Review App facilitates human-in-the-loop workflows. It allows domain experts to provide feedback and customise evaluation criteria without the need for spreadsheets or custom-built applications. This tool is designed to enhance the evaluation process, making it more efficient and accessible.

Batch AI offers a provision-less batch inference capability. It enables companies to run batch inference with a single SQL query, eliminating the need for infrastructure management.

Senior Director of Product for AI/ML at Databricks, Craig Wiley, said: "Many enterprises still struggle to deploy AI agents in high-value use cases due to concerns around accuracy, governance, and security. For these organisations, it’s confidence, not just technology, that presents the biggest hurdle to extracting the full data intelligence benefits of Generative AI. The new tools address these challenges head-on, enabling businesses to move beyond pilots and into full-scale production with AI agents they can trust."

CTO of Altana, a customer of Databricks, Ian Cadieu, said: "Batch AI with AI Functions is streamlining our AI workflows. It's allowing us to integrate large-scale AI inference with a simple SQL query—no infrastructure management needed. This will directly integrate into our pipelines cutting costs and reducing configuration burden. Since adopting it we've seen dramatic acceleration in our developer velocity when combining traditional ETL and data pipelining with AI inference workloads."

Altana has reported increased developer velocity by combining traditional ETL and data pipelining with AI inference workloads using these tools. This integration is said to have streamlined their AI workflows, reducing costs and configuration burdens.