AI Briefing#tracing
The latest AI and developer news about #tracing, with the original source and a short summary.
The latest AI and developer news about #tracing, with the original source and a short summary.
Upgrading @vercel/otel to 2.3.0 enables automatic trace export for Node.js daemons using a provided Unix socket.
The new Traces page supports KQL search and live streaming, while retention increases to 3 days for Hobby and 14 days for Pro and Enterprise plans.
The new tool extends automatic tracing beyond Workers to security rules, caching, and routing, with new pricing effective December 1, 2026.
New unified pricing for logs and traces takes effect December 1, 2026, with Logpush now available on all self-serve plans.
Vercel has launched an always-on tracing feature in beta that samples production traffic in real time.
Vercel AI Gateway exports OpenTelemetry traces for all requests via Drains.
Vercel Logs' Traces feature now supports Tree and Waterfall views, allowing you to identify performance bottlenecks directly within the logs.
Because AI agents follow a non-deterministic reasoning process, they require a different approach to observability and evaluation than traditional software.
Raindrop Workshop provides a local debugger that helps with agent tracing and evaluation.
Signals is a lightweight technique for selecting meaningful agent traces without LLM judges.
Agents get better fast only when expert judgment is built into evaluation and verification loops.
This covers how to trace and evaluate the behavior of AI agents built with smolagents in real time using Arize Phoenix.
LangSmith now supports the OpenTelemetry format, strengthening its distributed tracing and observability capabilities.