Summary
Tool calling enables AI models to interact with external systems and APIs, transforming basic chatbots into agents that execute real-world actions through a structured request-and-response loop. Databricks Agent Bricks provides a governed platform to build these agents grounded in enterprise data, featuring native support for the Model Context Protocol and Unity Catalog
Summary generated by brickster.ai. For the full article, follow the source link above.
More from Databricks Blog
Managing AI Coding Costs at Scale
AI coding tools deliver immense value: at Databricks, agentic coding has measurably...
What is an AI Assistant?
Enterprise AI assistants use large language models, retrieval-augmented generation, and agentic frameworks to execute workflows ranging from data analysis to autonomous pipeline management. Choosing the right tool requires evaluating data integration depth, governance controls, extensibility, and alignment with your team's existing workflows and skill levels.
What are Agentic Workflows?
Agentic workflows move beyond rigid, traditional automation by using autonomous AI agents that dynamically plan, select tools, and adapt to intermediate results at runtime. Deploying these workflows for enterprise efficiency and scalability requires strong governance, clear business objectives, and production-grade infrastructure.
Introducing OfficeQA Pro V2: A New Benchmark for Enterprise Grounded-Reasoning
Databricks released OfficeQA Pro V2, a new enterprise grounded-reasoning benchmark built from roughly 1,400 U.S. Treasury PDFs using a synthetic data pipeline. Benchmark testing
Kimi K3 from Moonshot AI is now available on Databricks through Unity AI Gateway
Moonshot AI’s most capable open-weight model, Kimi K3, is now available on Databricks through the Foundation Model API with full governance via Unity AI Gateway. Initially hosted in the US with comprehensive Zero Data Retention, the model integrates directly with your existing unified API, cost controls, guardrails, and observability workflows.