BriefsToolAvailable now
Databricks launches Unity Gateway Insights to analyze AI agent traces
The new feature uses Genie to identify token waste, recurring MCP errors, and inefficient model usage in agent workflows.
Summary
Databricks introduced Unity Gateway Insights to help teams analyze AI agent traces alongside business data. The tool uses Genie to surface token waste, recurring Model Context Protocol errors, and simple tasks running on expensive models. It also automates OpenTelemetry tracing for coding agents when engineers use the ug CLI.
What changed
- Added Unity Gateway Insights to analyze AI agent traces using Genie.
- Surfaces token waste, recurring MCP errors, and inefficient model usage.
- Automates OpenTelemetry tracing for coding agents launched with the ug CLI.
Availability
Available now“If your developers already run coding agents through Unity Gateway, you can generate your first report today:”
Founder takeaway
If your developers run coding agents through Unity Gateway, you can generate your first trace report today.
Source
Researched and drafted with AI from the official sources above, then checked automatically before publishing. Spotted a mistake? Tell us.
Related
More briefs
Google adds AI connected apps to search and gemini
Google is integrating grocery, finance, and home service apps into Search and the Gemini app for U.S. users.
Google Gemini1 min read
AWS adds Demand Center to AWS Partner Central
AWS launched Demand Center in AWS Partner Central, providing an AI-powered experience to manage demand generation campaigns.
AWS1 min read
AWS updates Quick with new AI agent flows and web features
AWS released updates to Quick, adding multi-agent orchestration, new deterministic workflow steps, an updated web app, and new connectors.
AWS1 min read
One email, every Monday
Briefs are published here through the day. Monday Heist is the email: one useful AI workflow, the files to use it, and the catch. The first issue is being prepared; subscribers get it first. Free, and you can leave in one click.
One email. Every Monday.