This post explores MCP sampling and illustrates how important guardrails are to protect clients against malicious servers.

The codebases of MCP servers tend to be early-stage API wrappers, far away in quality from existing SDKs. Non-determinism of LLMs adds…

The posts explores three approaches to manual OpenTelemetry instrumentation for OpenAI calls in Langchain and LlamaIndex.

Using automatic instrumentation to quickly assess which APIs are called by popular Python LLM demo apps.

Emergency procedures aim at stabilizing the system in a degraded state. When used properly, they result in faster incident response and …

This posts showcases strategies for shipping software in iterations, inspired by TDD, Coding Katas, and Testing in Production.

Explores how individuals can react to changes and focus their efforts to support the change to foster their own development.

This post focuses on 3 key elements of successfully preparing and announcing changes from the perspective of the change author and driver…

Operating software in production offers great insights into software quality. Learning from production incidents is key to improving…

Have you ever felt frustrated when you found a problem worth solving but it was not picked up by your colleagues nor supported by your…