8 min read
LLM Observability: The Few Signals That Actually Matter
Which LLM signals deserve a dashboard or a page: tokens by feature, latency split by phase, throttling, and sampled quality, using OpenTelemetry on Azure.
OpenTelemetry
8 articles
1 min read
Implementing Observability for AI Applications with OpenTelemetry
Observability is essential for AI applications. Without it, you're flying blind on costs, performance, and quality. Implement these patterns early and…
1 min read
Monitoring AI Applications: Observability Patterns for LLM Systems
LLM systems have unique characteristics: non-deterministic outputs, variable latency, complex cost models, and quality metrics that require semantic…
1 min read
Observability for LLM Applications: Tracing, Metrics, and Debugging
Log prompts and responses for failed interactions to a secure store for debugging. Implement sampling for successful calls to control storage costs while…
1 min read
OpenTelemetry for AI: Standard Observability for LLM Applications
OpenTelemetry provides a standardized way to instrument AI applications, ensuring your observability data is portable across different backends and tools.
1 min read
Tracing Frameworks for AI: Distributed Tracing in LLM Applications
Effective tracing reveals the inner workings of AI applications, helping you understand performance bottlenecks, cost drivers, and error sources across your…
1 min read
Tracing and Debugging AI Applications
Debugging AI applications is different from traditional software. Today I'm exploring tracing and debugging techniques for production AI systems.
1 min read
OpenTelemetry with Azure: Vendor-Neutral Observability
OpenTelemetry provides a future-proof approach to observability. By using vendor-neutral instrumentation with Azure Monitor as the backend, you get the…