Hi lk,

AI agents are changing how software is built and operated, but they also introduce new operational challenges that traditional observability wasn’t designed to solve. Unpredictable agent behaviour can lead to security and compliance risks, runaway token costs, and performance issues that are difficult to identify before they impact your business.

In this webinar we’ll show you how Splunk Agent Observability (powered by the acquisition of Galileo) provides end-to-end visibility across agents, LLMs, and infrastructure, helping teams improve performance, strengthen security, evaluate quality, and optimize token consumption.

In this session, you will learn about how Agent Observability helps teams:

• Observe performance across the entire AI stack to diagnose failures or errors by tracing dependencies, analyzing workflows, and tracking SLOs like latency and error rates
• Evaluate agent behavior from development through production with live evals that transition to cost-effective guardrails at scale
• Track tokenomics to understand how resources like GPUs and tokens are being used, optimize affecting costs, and correlate with quality and business value to ensure ROI
• Block sophisticated prompt-injection attacks, and inaccurate or harmful responses with custom SLM-powered guardrails

This session will be broadcast in English, but closed captions (subtitles) are available in English, French, German, Spanish, Portuguese, Polish and Italian.

Can’t attend live? Register anyway and we’ll send you the recording after the webinar!

Team Splunk