Splunk Blogs

Evaluating LLMs requires moving beyond general metrics to domain-specific, agentic, and adversarial benchmarks that reflect real-world performance.

Explore how the Vidar info-stealer uses virtualized code, anti-analysis tactics, and sandbox evasion to hide its activity. Learn how to identify and detect Vidar in your environment using actionable Splunk TTPs and analytics.

With Splunk MCP server, there’s no need to worry about how agents are using your data.

See what your coding agents cost before the bill arrives. Token Meter tracks Claude Code, Codex, and Cursor usage live — free, open source, and 100% local.

Master RAG observability with this end-to-end guide on tracing execution paths, implementing retrieval evaluators, and building incident playbooks to ensure production reliability.

Learn to diagnose the six primary hallucination patterns and implement a robust pipeline of retrieval, reranking, and guardrail enforcement to ensure reliability.

Splunk's new add-ons let teams track who used AI tools, what changed, and whether API keys were created or misused across ChatGPT, Claude, and other providers.

These .conf26 sessions will guide practitioners through building ML-based detections, understanding AI agent risks, and applying these techniques to real attack scenarios.

Learn the eval-to-guardrail lifecycle to transform offline evaluation criteria into runtime policies that intercept and block agent failures in production.