Splunk Blogs

We’re introducing splunkctl, the new Splunk CLI purpose built for the agentic era, and expanding the library of Splunk Agent Skills.

We’re introducing Business Journeys in Splunk Observability Cloud.

Public embedding leaderboards help shortlist models, but only corpus-specific evaluations confirm fit. Learn how to measure performance.

Rerankers optimize retrieval order for production RAG systems; learn how to select reranker architectures for your latency budget, and domain requirements.

How Splunk connects runtime and security context for faster response.

Understand the tradeoffs between LLMs and humans for generative AI evaluation

LLM judge vs SLM judge: an SLM costs 10-30x less and runs in 15-150ms, making 100% coverage affordable. See where each wins and when to make the switch.

Evaluate multi-agent AI systems using benchmarks that prioritize coordination, reliability, and policy adherence over simple accuracy scores to ensure production readiness.

How to build an SLM judge: See how to size the model, fine-tune with LoRA, validate it, and serve it in production.