LLM Monitoring & Tracing: AI Observability with Datadog
Enhance AI Observability: LLM Monitoring with Datadog
Created by Paulo Dichone
Explore practical strategies for monitoring and tracing large language model applications using Datadog. Gain hands-on experience with real-world AI workflows, focusing on performance, security, and cost optimization. Build the skills needed to ensure your AI systems are production-ready and reliable.
Packt | Apr 2026 | 247 min
What You Will Learn
You will work through practical exercises that guide you from initial Datadog setup to advanced monitoring of complex AI workflows. By applying tracing, tagging, and evaluation techniques, you will learn to identify issues, optimize performance, and maintain secure, cost-effective AI systems in production.
Key Features
- Set up Datadog to monitor and trace LLM workflows in real-world environments
- Debug and optimize multi-agent AI systems for better reliability and performance
- Apply cost control and security practices to keep AI applications efficient and compliant
Target Audience
Perfect for AI engineers, DevOps specialists, and data scientists aiming to improve observability in LLM-driven applications. If you have a basic understanding of cloud systems and software development, you will benefit from actionable skills to monitor, debug, and optimize AI workflows in enterprise settings.
