Live traffic

The Live page shows your agents’ real traffic as it happens. A turn is a prompt and the response to it, and each one appears as soon as it flows through an agent you’ve connected, so you can watch which model answered, how long it took, and whether a guardrail acted on it. Turns appear here only once an agent is connected and sending traffic. You connect an agent with the Switch Trust SDK, and from then on its prompts and responses stream to this page. Until traffic arrives, the page reads No data in last 24 hours.

​

Open the Live page

In Switch Trust, select Live in the sidebar.

​

Summary cards

Three cards across the top summarize the Last 24hr of traffic:

• Interactions shows how much traffic your agents handled.
• Actions shows the guardrail actions taken on that traffic, such as blocked or redacted turns.
• Top detectors shows which guardrail detectors fired most often.

Each card reads No data in last 24 hours until your agents send traffic.

​

Live turns

Below the cards, Live turns streams each turn as it arrives. The green indicator next to the heading shows the list is live and updating on its own. A results count tells you how many turns match, and you can:

• Search to filter the list.
• Use the Columns control to choose which columns the table shows.

By default the table shows these columns:

• Time is when the turn happened.
• Input is the prompt sent to the model.
• Output is the model’s response. A turn stopped by a guardrail has no output to show.
• Model is the model that answered, such as gemini-2.5-pro.
• Actions is the guardrail action taken on the turn. A red Blocked badge means a guardrail stopped the turn. No badge means no action was taken.

​

Choose columns

Select the Columns control and turn columns on or off. In addition to the defaults, you can show:

• Session groups the turn with others from the same session.
• Events lists the events recorded for the turn.
• Latency is the total time the turn took.
• Model supplier is the provider that served the model, such as Google.
• Model manufacturer is the organization that built the model.
• Caller IP is the address the request came from.
• Model latency is the time spent in the model itself.
• App name is the connected app that produced the turn.
• App asset ID is the identifier of that app.
• Last seen is when the app was last active.

​

Turn detail

Select any row to open the Turn detail panel. Turn info lists the full record for the turn:

• ID — the turn’s unique identifier.
• Time — when the turn happened.
• Prompt text and Response text — the prompt and the model’s reply in full.
• Tokens and Cached tokens — the token usage for the turn.
• Model name, Model supplier, and Model manufacturer — the model that answered and who serves and builds it.
• Caller IP — the address the request came from.
• Prompt guardrail and Response guardrail — the guardrail action applied to the incoming prompt and the outgoing response.
• Total latency and Model latency — the end-to-end time and the portion of it spent in the model.
• App name and App asset ID — the connected app that produced the turn and its identifier.
• Cost — the cost of the turn.

Events shows the turn’s messages: the User prompt and the Agent response. Expand either one to read its full text.

​

Related