Skip to main content

Agent overview

The Overview tab answers whether the agent is working and what it is costing, over a window you pick in the header.

Who can use it: anyone who can open the agent.

The five figures​

An agent's page in Studio: the header with the agent's initials, name, version and status, its tools and knowledge counts, channel, owner and dates, the Range selector, Publish for the waiting draft and Edit, both dimmed because the agent belongs to another builder, the row of tabs from Overview to Settings, and the Overview tab with tiles for conversations, CSAT, tool success, latency and spend above the traffic chart, top tools, classification mix and recent conversations, with About and Health on the right.An agent's page in Studio: the header with the agent's initials, name, version and status, its tools and knowledge counts, channel, owner and dates, the Range selector, Publish for the waiting draft and Edit, both dimmed because the agent belongs to another builder, the row of tabs from Overview to Settings, and the Overview tab with tiles for conversations, CSAT, tool success, latency and spend above the traffic chart, top tools, classification mix and recent conversations, with About and Health on the right.
The agent page is where a published agent lives. The header summarises it, Edit opens a draft in the builder for the agent's owner or an administrator, and the tabs cover its behaviour, evidence and release history.
FigureWhat it is
ConversationsSessions in the window, with the change against the window before
QualityThe evaluation result, named for whatever measure produced it
Tool successThe share of tool calls that succeeded, with the change in points
p50 latencyThe median, with the 95th percentile beside it
SpendMonth-to-date, with the cost per conversation

The quality tile renames itself for the measure behind it, so it can read as groundedness, thumbs, satisfaction or simply quality. Read the label, not the position.

The spend tile says no billing source wired rather than showing a zero when nothing is metering.

The range picker offers the last hour, day, week, fortnight or month, and defaults to a week.

Traffic and tools​

The chart plots conversations across the window. Top tools used ranks the tools by calls with their success rates.

Classification mix will be empty. No classifier is wired for any agent today, so the card says so rather than showing an empty chart.

Recent conversations lists the last sessions with their classification, turns, latency and outcome. Selecting one opens it in the Traces tab.

The health rail​

Six rows, and it is worth knowing which of them can actually say something.

RowWhat it can report
ReleaseThe release it was minted from, or that none was
Eval suiteA pass rate, or that no evaluation has run
Latency budgetThe measured p95, and that no budget is set
Cost capThe measured spend, and that no cap is set
KB freshnessWhen the attached knowledge bases last synced
Drift on intentNothing, ever

Latency budget and cost cap have no setting anywhere to configure, so those rows report a measurement and state plainly that nothing is bounding it. They are deliberately neutral rather than green.

Drift on intent always reads that no drift source is wired. There is no monitoring service behind it.

The cost row adds unpriced with a count when the gateway could not price some calls. Read that as the spend being a floor.

Channels and activity​

Channels lists where the agent answers, taken from the agent's own surfaces, with a live or draft pill. There are no per-channel figures anywhere in the platform, so the line under each reads as a dash.

Activity is the last few publishes, with who made each and when.

Describes the platform as of .

Was this page helpful?