Block uses Buzz and Unity Gateway to collaborate with AI agents
Understand this story
Block has developed Buzz, an open-source collaboration space that lets employees work together with AI agents in channels, threads, and direct messages. When employees create agents, they can choose a model or coding harness for each agent and can set Databricks as the inference provider, selecting from the models offered by Unity Gateway. Buzz connects to frontier models from OpenAI, Anthropic, and Google as well as some open-weight models through Databricks Unity Gateway in a single integration. Databricks says that Buzz, as an open-source project, is not tied to a specific model and can be self-hosted, meaning it can run privately on one's own network or systems, and users can decide for themselves how agents are deployed and configured.
AI overview based on source reports · Updated 2 days ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Databricks BlogHow Block powers collaborative AI agents with Buzz and Unity Gateway
Block developed Buzz, an open source, model-agnostic collaboration space where employees and AI agents work together in group discussions, focused conversations, and one-on-one exchanges, with users choosing the model or coding harness behind each agent. Databricks Unity Gateway provides the model access layer, letting Buzz users select Databricks as their inference provider and choose from frontier models from OpenAI, Anthropic, and Google plus select open-weight models through a single integration. Block has also been experimenting with multi-agent workflows, such as a more capable model coordinating agents powered by smaller, more efficient models, and developed an internal benchmarking approach for these agent teams.
Activity for this story
- Current comparable activity
- 3
- Peak comparable activity
- 9Nov 13 01:00
- Change in the past 24 hours
- -51%
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.