AI Briefing#observability
The latest AI and developer news about #observability, with the original source and a short summary.
The latest AI and developer news about #observability, with the original source and a short summary.
Sharing a case study on improving internal observability and fostering contributions by leveraging existing infrastructure and AI agents.
Developers can now request interactive flamegraphs for active Workers and Durable Objects via the CLI or Cloudflare Dashboard to identify resource bottlenecks in production.
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.
Using NVIDIA NeMo Relay to trace Hermes Agent before and after harness changes revealed that the success rate increase for Qwen3 Coder 30B was partly due to eliminating provider errors, while average LLM calls and duration increased.
Cloudflare's new open beta feature, Issues, groups production errors and automatically sends diagnostic context to coding agents like Claude Code and Cursor.
The new vercel traces search command returns up to 100 spans from the last hour by default, supporting filters via KQL and JSON output for automation.
LangSmith Engine v2 introduces red teaming and automated fix validation, while Managed Deep Agents v0.8 adds user-level memory and built-in web search.
The new feature includes P75 and P95 memory metrics in the dashboard and exposes memoryUsedBytes data via the vercel metrics CLI command.
Trajectories project nested traces into a linear, readable view of agent actions, enabling faster debugging and SME review.
Cloudflare has launched Worker Previews, an isolated, production-like environment per branch for code changes by AI agents.
Yeogi-eottae built an APM scatter chart by integrating OpenTelemetry and ClickHouse to visualize the distribution of individual requests.
The open-source proxy 'Vessel' has been released, allowing users to log Ollama requests and compare them with other models.
KT Cloud unveiled a strategy to redesign development and operations for the AI era, centered on AIDC and its cloud platform.
kt cloud is building an AIOps model that connects scattered cloud data to support AI-driven operational decision-making.
LangChain released Polly and a CLI to support complex deep agent debugging via LangSmith.
LangSmith Engine has improved agent issue detection performance by more than 2x and fix performance by 25%.
PandaProbe, an open-source platform that automatically diagnoses AI agent failures and recovers them using validated rules, has been released.
The SRE team at Yeogi-eottae Company built Alert Adviser, which uses AI to analyze Grafana alerts and automatically trace incident root causes and impact scopes.
Vercel has launched an always-on tracing feature in beta that samples production traffic in real time.
Vercel has started supporting the recording and analysis of custom metrics in Observability.
kt cloud built an Observability Alert platform based on the LGTM stack, achieving organizational isolation and integration with centralized monitoring.
LangSmith BYOC has launched as a generally available service running within customers' AWS accounts and VPCs.
Vercel has integrated coding agent setup and model/cost management through AI Gateway.