← AI Agents AI Agents
Browse AI Agents
Topic Hub

Production Engineering

Observability with OpenTelemetry, evaluation pipelines, CI/CD, cost attribution, fallback strategies, and deployment hardening.

LLM Observability with OpenTelemetry for Agents: Production Guide OpenTelemetry GenAI Semantic Conventions for Agent Spans Tracing Multi-Agent Workflows with OpenTelemetry Measuring P99 Latency in AI Agents LLM-as-a-Judge: Agent Output Evaluation Tool Use Correctness Evaluation: Scoring and CI Validation Multi-Turn Agent Evaluation Ragas: Thread-Level Scoring Guide Braintrust: CI/CD Agent Evaluation Setup Agent Cost Attribution and Token Tracking Guide Prompt Versioning and Drift Detection for LLM Agents CI/CD Pipelines for LLM Applications: Production Blueprints Automated Rollbacks for AI Agents Managing Non-Deterministic Agent Outputs Sandboxing Code Interpreter Agents: Secure E2B and Docker HITL Escalation with LangGraph Interrupt Nodes Fallback LLM Providers for Agent Reliability: Implementation Guide OpenInference vs OpenTelemetry GenAI: LLM Tracing Spec