Databricks details how Block's Buzz uses Unity Gateway for model access
Start here
Block built Buzz, an open source collaboration workspace where employees and AI agents work together in group discussions, focused conversations and one-on-one exchanges, and it uses Databricks Unity Gateway as the model access layer, Databricks said in a blog post. When employees create an agent in Buzz, they can pick the model or coding harness behind it and select Databricks as their inference provider, reaching frontier models from OpenAI, Anthropic and Google plus select open-weight models through a single integration. Because Buzz is open source and model-agnostic, it can be self-hosted and run privately on a user's own network or system. Block engineers are also experimenting with multi-agent setups in which a more capable model coordinates agents running smaller, more efficient models, and have built an internal approach to benchmarking these agent teams.
Generated from reports · updated 13 h ago
Report timeline
Follow the reports to see the event from different sides.
- Databricks BlogHow Block uses Buzz and Databricks Unity Gateway to run collaborative AI agents
Block built Buzz, an open source collaboration workspace where employees and AI agents work together in group discussions, focused conversations and one-on-one exchanges, and uses Databricks Unity Gateway as the model access layer. Employees can create agents, pick the model or coding harness behind each one, and select Databricks as their inference provider to reach frontier models from OpenAI, Anthropic and Google plus select open-weight models through a single integration. Block engineers are also experimenting with multi-agent setups where a more capable model coordinates agents running smaller, more efficient models, and have built an internal approach to benchmarking these agent teams.
Heat for this event
Not enough continuous observations yet to draw a trend.