MonitorOperateCopy pageMonitor, test, and optimize your agents at scale.This section provides tools and best practices for running production agents, from testing and quality assurance to analytics and cost optimization. Monitor and optimize GoalGuideDescriptionList users by external IDUsersSee end users and open their conversationsSearch transcriptsSearching conversationsKeyword and semantic search in Conversation historyRun A/B testsExperimentsTest agent configuration changes with live trafficTest agent behaviorTestingCreate and run automated tests for your agentsAnalyze conversation qualityConversation analysisExtract insights and evaluate conversation outcomesTrack metrics & analyticsAnalyticsMonitor performance metrics and conversation historyConfigure data retentionPrivacySet retention policies for conversations and audioReduce LLM costsCost optimizationMonitor and optimize language model expensesManage agents as codeCLIVersion control and deploy agents from your terminalManage agents from ClaudeHosted MCPCreate and update agents from any MCP client Next steps UsersList end users by ID and drill into their conversationsExperimentsRun A/B tests to optimize agent performanceTestingSet up automated testsAnalyticsView performance metricsSpotlightReview real-time insights, sentiment, and discovered topicsConversation analysisAnalyze conversations
