» Tag
observability
81 postsProduction RAG at Scale: Lessons from Processing 10,000+ Listings Daily
Insights on RAG pipeline stability, chunking strategies, and cost control from processing job listings.
Guide to Instrumenting an LLM Agent with OpenTelemetry
Learn how to instrument your LLM agent with OpenTelemetry using GenAI standards and auto-instrumentation.
Schrödinger's Service: Why Your Microservice Is Both Up and Down
Microservices' health cannot be determined by health checks alone. Explore the importance of comprehensive observability in engineering.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comWhen AI Agents Orchestrate Agents: The Observability Gap
When AI agents spawn other agents, failures often stay invisible. Sentry's trace-based observability approach reveals exactly which agent introduced the problem.
Sentry now provisions in two commands via Stripe Projects
Sentry joins Stripe Projects as a provider, letting developers and AI agents provision monitoring, DSNs, and billing with just two CLI commands.
Exporting Next.js Traces with OpenTelemetry
Next.js automatically traces requests, but you need an exporter to see them. Learn how @vercel/otel sends traces to Sentry or any OTLP backend.
AgentSight: eBPF Observability Tool for AI Agents Without Code Changes
AgentSight offers eBPF-based observability for AI agents, capturing LLM API calls without code changes.
Bitdrift Scales to 121 Million Concurrent gRPC Connections
Bitdrift successfully managed 121 million concurrent gRPC connections during the T20 World Cup.
I Built a Simple Tool to Observe My AI Agents' Activities
Otterscope, a tool I built for monitoring small LLM agents, offers an efficient and user-friendly solution for observing agent activities.
Reading Agent Traces Reveals What Evals Can't Decide
An agent built for AI Engineer World's Fair invented fake speakers. Reading agent traces, not evals, caught it—key lessons on model choice, cost, and observability for engineers.