Features
Real-time detection of Python script execution on endpoints
Monitor script access to databases, internal APIs, and sensitive data
Alert-based monitoring with risk classification per event
Detailed alert context: code snippets, recommended actions, execution history
Centralized inventory of Python scripts and AI agents by area, user, machine
Policy enforcement at runtime without blocking productivity
Audit trail with who, what, when, how for compliance reporting
Executive dashboard for risk trends and governance visibility
Integration with BotCity Orchestrator for approved automation execution
Orchestrator versioning, failure handling, and reprocessing
Insights module for adoption metrics and risk posture analysis
Multi-language support: English, Portuguese, Spanish
Endpoint governance across distributed workstations and environments
Shadow Python detection: AI-generated or business-user scripts outside IT control
Trace agent executions step by step
Monitor real-time dashboards with cost tracking
Online LLM-as-judge evals for quality scoring
Automated insights with unsupervised topic clustering
SmithDB purpose-built for agent traces
Sub-second query performance across millions of traces
Full-text search with inverted index
JSON key-path filtering and trajectory queries
Self-host SmithDB inside your VPC
LangSmith Engine for autonomous issue detection and fixes
Deploy and scale agents with LangSmith Deployment
Sandboxes for safe agent-generated code execution
Fleet agents for no-code agent creation
Supports Python, TypeScript, Go, Java SDKs
