Block developed Buzz as an open-source collaborative platform where human workers and AI agents interact within shared individual or group conversations. Databricks Unity Gateway underpins the workspace by providing a single integration access point to frontier systems and open-weight models from Google, Anthropic, and OpenAI. The platform also includes a built-in agent that utilizes a lightweight version of Goose alongside other coding harnesses. This environment allows engineers to manage expenses by testing multi-agent workflows where powerful frontier models orchestrate tasks executed by smaller, more efficient models.
Key points
Human employees can monitor automated inter-agent discussions in real time and interject…: Human employees can monitor automated inter-agent discussions in real time and interject with added context or clarifying questions.
Organizations can lower overall operating costs by orchestrating workflows using high-cap…: Organizations can lower overall operating costs by orchestrating workflows using high-capability models to coordinate smaller, more efficient agents.
Unifying multi-model inference inside a single conversational space eliminates the ineffi…: Unifying multi-model inference inside a single conversational space eliminates the inefficiency of employees constantly toggling between isolated artificial intelligence applications.
Sources checked by our analysis pipeline: 1
by Bradley Axen, Brandon Kvarda, Julia Powell and Kelly Albano
Inside Block, Buzz brings employees and AI agents into a shared workspace. With Databricks Unity Gateway, employees who use Buzz can access frontier and open-weight models, experiment with different agent harnesses, and find the right combination based on the efficiency frontier for each task.
As AI agents become part of everyday work, Block’s teams needed a way to work with agents in the same place they work with each other. Block developed Buzz, an open source collaboration space where people and AI agents can work together in group discussions, focused conversations, and one-on-one exchanges.
Buzz brings agents into the same collaborative environment as employees. Users can create an agent, choose the model or coding harness behind it, and bring that agent into a conversation with colleagues. Rather than switching between different AI tools, teams can work with multiple agents in one place.
At Block, Databricks Unity Gateway helps power the Buzz experience by providing access to a broad selection of frontier and open-weight models through a single integration. That gives…
Enterprise teams can now interact directly with Databricks data intelligence without leaving their primary chat channels. The integration brings source-cited responses, automated actions, and scheduled data analyses straight into collaborative conversations to speed up operational decisions. Strong permission safeguards ensure that sensitive assets remain restricted based on the querying user's established access profile.
Enterprise artificial intelligence teams are adopting structured frameworks to reliably deploy complex systems that orchestrate tools, internal knowledge, and external APIs. Conventional continuous integration and unit testing fall short because of non-deterministic behavior and independently shifting external dependencies. To guarantee consistent performance, organizations are instituting rigorous evaluation cycles anchored by business-approved gold standards.
Deploying enterprise AI agents creates significant compliance and security hazards when large language models control user identity parameters during document searches. System designers can mitigate data leakage and prompt injection risks by taking identity authorization away from the model and placing it entirely within trusted code layers. This approach guarantees that internal corporate knowledge bases return only the materials permitted for a verified employee profile.