Features
Continuous high-resolution profiling timelines
Operation duration and resource utilization tracking
LLM generation tracing with per-step timing
Token throughput and latency breakdowns
System-level metrics for CPU, GPU, accelerators
Error monitoring for device-level failures
Inference telemetry for AI agents (autodebug)
Low-overhead CUDA kernel attribution
Claude Code integration for AI debugging
Profiler CLI and Python API
Support for vLLM, SGLang, PyTorch, TensorRT-LLM
AI agent on-call triage and investigation
Co-work with agents during incident resolution
Automatic root cause analysis for complex issues
Background agents for scheduled workflows
Custom agents via MCP, API, and Skills
Tribal knowledge capture from chats and runbooks
Mult-agent council for improved RCA accuracy
SAML SSO, RBAC, and admin controls
Data redaction, encryption, and retention
Activity and support access logging
SOC 2 Type II certification
HIPAA and GDPR compliance
Severity-based vulnerability triage
Integration with Slack and Microsoft Teams
Resolve AI Workbench for collaborative investigation
