Последние новости AI & ML от Tech News
We stopped learning about production failures from other teams by splitting observability into two planes: telemetry that's always on, and notificat…
On September 30 someone filed an issue on the OpenTelemetry browser SDK. startBrowserSdk was throwing TypeError: URL.parse is not a function on olde…
The Boundary Problem OpenTelemetry documentation emphasizes that implementers are responsible for protecting sensitive data, noting that the system…
This metric looks helpful: agentRuns . add ( 1 , { runId , userId , prompt , toolArguments : JSON . stringify ( args ), error : error ?. message , }…
If you run Dagster pipelines in production, you've probably wanted distributed tracing at some point — seeing exactly how long each op/asset took, h…
Когда выбирают агент для телеметрии, обычно сравнивают поддержку протоколов, потребление CPU и удобство конфигурации. Я бы начал со следующего вопро…
A customer called to say OTPs weren't reaching them. We checked the logs. Every request came in. Every SMS went out. The provider said delivered. No…
This article introduces OpenTelemetry Go Compile-Time Instrumentation v1, enabling zero-code, build-time observability for Go applications. Go was t…
Headline: Next.js's instrumentation.ts file and its onRequestError hook give the App Router real distributed tracing and centralized error reporting…
I ran a penetration test on my own infrastructure last week. No Burp Suite, no exploit fired at production, no CVE popped. The whole engagement came…
You shipped your AI agent. It answers questions, calls tools, retrieves documents, and mostly does the right thing. Mostly. When it does the wrong t…
For a long time, my mental model of observability was this: you import an SDK, sprinkle some calls through your code, each call fires off data to a…
Трейс ИИ-агента можно открыть в обычном "дереве" и найти медленный вызов или спан с ошибкой. Но по дереву трудно восстановить логику запуска: скольк…
Вызов инструмента ИИ-агентом легко теряется между моделью, MCP-клиентом, сервером и внешним API. В конце июля сразу два события показали, каким спос…
How this piece came together. A Zenn writing contest put OpenTelemetry back on my radar, and this is the record of learning it by doing — picking it…
When I started building agent-exec-trace , I thought I knew where the difficulty would be. OSS agent-exec-trace is an observability layer for AI age…
A regression came in for our German enterprise users on the support agent. Quality had dropped for that one cohort, and I opened the trace store exp…
Для проверки сквозного трейсинга GenAI-приложения мы взяли OpenTelemetry Demo 3.0. В обновлённом стенде уже были сервисы chatbot , agent и mcp , а т…
Agentic DevOps Needs Observability: Trace GitHub Copilot with OpenTelemetry An agent can read files, call a model, run tools, delegate to a subagent…
The constraint that shapes everything A refactor that recently landed in a codebase I work in replaced our metrics god class with per-subsystem modu…
When metrics exporters retry failed requests, they can accidentally create a subtle but serious problem: duplicate ingestion. That was the motivatio…
A follow-up to How Old Is My Data? The failure mode that gets worse when a machine is reading the data In a classic dashboard, stale data is a human…
If you run more than a handful of OpenTelemetry Collectors, you already know the pain: a config change means SSHing into boxes, redeploying DaemonSe…
Metrics and logs were the easy part, and I wasn't ready for traces. It took me a while to get it, first getting a grasp on the vocabulary, then putt…
The VictoriaMetrics folks now have a component for each OTel signal: VictoriaMetrics for metrics, VictoriaLogs for logs, and VictoriaTraces for trac…
The problem A single LLM call is easy to reason about. You send a prompt, you get tokens back, you log the latency and you move on. A swarm is not t…
-and added the one signal it was missing Track 01 — AI & Agent Observability. A hackathon project built from scratch, July 20–26, 2026. There's…
We ran Agent K against 12 seeded production incidents. It named the correct root cause 5 times out of 12 — 3 out of 9 if you discard the runs we cou…
By Team ThunderBoltz · Agents of SigNoz Hackathon · Track 1: AI & Agent Observability In the kickoff Q&A for the Agents of SigNoz hackathon,…
Built for the WeMakeDevs Agents of SigNoz hackathon, July 2026. Mission Control. The graph is the swarm, the river underneath it is the live span st…