# Introducing Unity Gateway Insights

> Source: <https://www.databricks.com/blog/introducing-unity-gateway-insights>
> Published: 2026-11-18 17:43:28.538074+00:00

**Key takeaway:** Unity Gateway Insights samples agent sessions, groups them into workstreams, and ranks failing MCP tools, bloated context, frontier models on simple tasks, and repeated workflows by tokens at stake, with each finding linked to example sessions.

Automatically discover inefficiencies in your AI usage

by  [Adam Gurary](https://www.databricks.com/blog/author/adam-gurary), [Alkis Polyzotis](https://www.databricks.com/blog/author/alkis-polyzotis)  and  [Vishnu Kannan](https://www.databricks.com/blog/author/vishnu-kannan) 

When looking to cut AI costs, teams often start with budgets or open-source models. But agent traces can reveal other opportunities to save. At Databricks, trace analysis surfaced several: offline replays showed no performance gain from upgrading from Opus 4.8 to Opus 5, so we stayed on the cheaper 4.8; fixing common MCP errors recovered an estimated [$1.2M in costs a year](https://www.databricks.com/blog/how-we-eliminated-1-million-year-wasted-ai-agent-spend-one-hour); and traces showed that simple prompts were going to expensive models, prompting us to adopt [Smart Routing](https://www.databricks.com/blog/smart-routing-unity-ai-gateway-match-frontier-quality-30-lower-cost-task). 

Today, we’re introducing **Unity Gateway Insights**, which automatically uses Genie to analyze millions of agent traces alongside your business data and ontology. It surfaces where tokens are being wasted: MCP errors that keep recurring, simple tasks running on expensive frontier models, and repeated workflows worth turning into shared skills, all in the context of your business and under the same governance as your other data.

If you already have traffic flowing through Unity Gateway, open AI Gateway > Observability > Insights and generate a report for the last day, 7 days, or 30 days. Insights then writes a report on the tokenomics of your coding agent rollout that answers the following questions:

Each finding links to example sessions, so you can open the traces behind it.

You can add up to 10 questions of your own to a report, such as whether the newest model is worth it for your team's work. To dig further, continue the conversation with Genie. Ask which MCP server wasted the most tokens this month and who owns it, and you have a bug report ready to send.

Here's what's behind each kind of waste Insights reports:

Finding this kind of waste requires a full record of every step of every agent session: inputs and outputs, tool calls, subagents, intermediate steps, latency, and token cost. A standalone gateway records only the requests that pass through it. Capturing the rest of each session means instrumenting every coding agent yourself, then exporting the traces to a data platform to analyze them.

Pointing Claude Code at those traces still leaves you to design the investigation yourself, with no map of your business like the [Genie Ontology](https://docs.databricks.com/aws/en/genie/genie-ontology/) provides. Insights runs the investigation we developed while rolling out coding agents to thousands of Databricks engineers. It samples sessions and groups them into workstreams by kind of work. Then it checks each workstream for failing MCP tools, bloated context, frontier models on simple tasks, and repeated workflows, and ranks what it finds by the tokens at stake. It depends on four things a standalone gateway can't have:

If your developers already run coding agents through Unity Gateway, you can generate your first report today:

[Unity Gateway](https://www.databricks.com/blog/tag/unity-gateway)  and  [Genie](https://www.databricks.com/blog/tag/genie)

Subscribe to our blog and get the latest posts delivered to your inbox.
