Databricks Introduces New Tools To Build Scalable, Trusted AI Agents

Even as reports indicate that 85% of global enterprises now use generative artificial intelligence, the most advanced models struggle to deliver business-specific, accurate, and well-governed outputs. This is primarily because they lack awareness of enterprise data. 

To help enterprises scale AI agents beyond the pilot phase to successful production with greater confidence, data and AI company Databricks has announced new tools. The new tools will enable organisations to deploy AI agents in high-value, mission-critical applications while ensuring accuracy, governance, and ease of use. The tools are:

Centralised Governance For AI Models: Organisations can integrate and manage open source and commercial AI models in one place with Mosaic AI Gateway support for custom LLM providers. The Mosaic AI Gateway provides unified governance, monitoring, and integration across all models.

Simplified Integration Into Existing App Workflows: The AI/BI Genie Conversational API suite enables developers to embed natural language-based chatbots directly into custom-built apps or popular productivity tools like Microsoft Teams, Sharepoint, and Slack. With the API, users can submit prompts and receive insights, and the API retains context across multiple follow-up questions within a conversation thread.

Streamlined Human-In-The-Loop Workflows: The upgraded Agent Evaluation Review App makes it easier for domain experts to provide feedback, send traces for labelling, and customise evaluation criteria, without needing spreadsheets or custom-built applications. By making it easier to collect structured feedback, teams can refine AI agent performance and drive improvements. 

Provision-Less Batch Inference: This tool offers a new way to run batch inference with Mosaic AI using a single SQL query, eliminating the need to provision infrastructure while enabling unstructured data integration.

“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,” said Craig Wiley, senior director of product for AI/ML, Databricks. “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.”