Monitoring Agentic AI Applications with Splunk Observability Cloud

Instrument a LangChain-based agentic AI app with OpenTelemetry and use Splunk Observability Cloud to surface quality issues and AI security risks.

Splunk Observability for AI monitors the performance, quality, security, and cost of AI application stack. It includes the following:

• AI Agent Monitoring, which monitors the performance, quality, security, and cost of LLM and agentic applications.
• AI Infrastructure Monitoring, which monitors the health, availability, and consumption (or usage) of AI infrastructure.

This workshop provides hands-on experience deploying and working with these capabilities in Splunk Observability Cloud. This includes:

• Understanding how to connect an Azure account to Splunk Observability Cloud to capture AI infrastructure-related metrics.
• Exploring out-of-the box dashboards and navigators related to AI infrastructure.
• Reviewing the architecture of an Agentic AI application built with LangChain and LangGraph.
• Practice deploying an Agentic AI application and instrumenting it with OpenTelemetry.
• Exploring how metrics, traces, and logs can be used in Splunk Observability Cloud to understand agent performance.
• Practice modifying an Agentic AI application to use tool calls and agents.
• Practice adding quality issues to an application and detecting them with Splunk Observability Cloud using semantic quality evals.
• Practice adding AI Defense instrumentation to the application and security risks, and detecting them with Splunk Observability Cloud.