Skip to main content

Documentation Index

Fetch the complete documentation index at: https://koreai.mintlify.app/llms.txt

Use this file to discover all available pages before exploring further.

Monitor agent performance, sessions, and request-level traces across your workspace. Workspace Analytics gives you visibility into how agents behave in production — from aggregate metrics to individual session transcripts and step-level execution logs.
  • Navigation: Settings > Analytics
  • Required role: Owner, Admin, or Operator; Member for project-scoped views.
Use the All Projects dropdown and time range controls (24h, 7d, 30d, 90d) to filter data across all tabs.

Agents

The Agents tab shows aggregate performance metrics for all agents in the selected project and time range.
Agent performance metrics appear once agents start processing sessions.

Metrics

MetricDescription
Total sessionsNumber of agent sessions in the selected time range.
Avg. session durationMean time from session start to last message.
Resolution ratePercentage of sessions that reached a successful outcome.
Avg. messages per sessionMean number of user and agent messages per session.
Total tokens consumedInput and output tokens across all models.
Total estimated costCalculated LLM cost for the period.
Error ratePercentage of sessions that encountered errors.
Filter by date range, project, agent, or model. Charts show session volume over time, token usage, cost trends, top agents by session count and cost, and error breakdown.

Sessions

The Sessions tab lists individual user sessions across all agents in the selected project and time range.
Session data appears once agents start processing requests.

Browse sessions

  1. Go to Settings > Analytics > Session Explorer.
  2. Search by session ID, user message content, or agent name.
  3. Filter by status, date range, or agent.
  4. Click a session to view the conversation transcript, tool calls, model usage, state transitions, and metadata.

Traces

The Traces tab provides a step-by-step execution log of agent runs. It offers two views: Event Stream and SQL Query.
Trace events appear once agents start processing sessions.

Event Stream

The Event Stream view shows a chronological log of all agent events in the selected project and time range. Each trace records a span tree — a hierarchical view of all operations:
Event typeWhat it captures
LLM callsPrompt, response, tokens, and latency.
Tool executionsName, input, output, and duration.
Step transitionsFlow step changes for agents with a FLOW section.
Guardrail evaluationsCategory, score, and decision.
Knowledge base queriesQuery text, retrieved chunks, and relevance scores.
Filter events by type:
FilterDescription
AllShow all event types.
LLMLLM call events.
ToolTool invocation events.
DecisionAgent decision and routing events.
ErrorEvents that resulted in an error.
HandoffAgent handoff and delegation events.
AgentAgent lifecycle events.
SessionSession start and end events.
Use the search bar to find events by session ID, agent name, or event type. The total event count is shown next to the search bar. Trace search syntax:
OperatorExampleDescription
agent:agent:customer-supportFilter by agent name.
status:status:errorFilter by outcome.
model:model:claude-4-sonnetFilter by model used.
duration:>duration:>2sFilter by total duration.
tokens:>tokens:>5000Filter by token count.

SQL Query

The SQL Query view lets you run custom queries against trace event data.
Admin access is required to use the SQL Query view.
ControlDescription
Example QueriesA dropdown of pre-built queries to help you get started.
SQL editorWrite or paste a SQL query. Use {tenantId:String} and {projectId:String} for isolation.
ClearClear the current query from the editor.
ExecuteRun the query and view results.