Operations | Monitoring | ITSM | DevOps | Cloud

Scope: this guide covers tools for tracing and evaluating the LLM apps and agents your team builds. If you also want the second meaning of AI observability, where AI agents investigate production incidents, read our guide to the best AI observability tools of 2026.

TL;DR On October 21, 2026, PHP released emergency patches for two critical flaws known together as PHP2Shell (CVE-2026-109618 and CVE-2026-109619). An attacker with no credentials can use them to run code on a PHP web server, in some cases with a single HTTP request. Upgrade to PHP 8.2.35, 8.3.36, 8.4.27 or 8.5.12 now. Then go through your logs, because exploitation attempts were recorded before the patch shipped. In this post.

TL;DR Logz.io AI Observability provides end-to-end tracing for AI agents and LLM applications. Built on OpenTelemetry, it lets you trace every request from prompt to backend service, visualize multi-step agent execution, isolate root causes across models and infrastructure, and track token usage per step, all alongside your existing logs, metrics, and traces.

TL;DR Cutting telemetry volume is only half of cost management. The other half is sending each signal to the right destination and storage tier, adjusting policies as traffic and incidents change, and rolling out every change in phases that teams can measure and reverse.

TL;DR Log and telemetry costs climb because every record gets shipped, indexed, and stored at the same priority. The fix starts before the backend: classify signals by operational value, filter what has none, and sample high-volume streams so you keep the evidence that matters and stop paying for the rest.

TL;DR “AI observability” now describes two different jobs. One is watching the LLM apps and AI agents your team ships: prompts, tool calls, token spend, and output quality. The other is putting AI agents to work on your production telemetry so incidents are already being investigated by the time an engineer logs in. Most engineering orgs in 2026 need both, and very few tools cover the two well.

TL;DR: OrionIQ AI agents, available inside the logz.io platform, now learn from your feedback. Rate any agent run, thumbs up or thumbs down, say why, and the agent re-reads its own run, finds the decision behind the outcome, and writes a lesson. The next run of that agent in your account starts with the lesson in hand. It works for every OrionIQ AI agent, from Alert AI Analysis to scheduled and marketplace agents. Lessons never cross accounts or agents, and you control what the agent keeps.

Open 360 AI chat can now do more than investigate and explain. With new Logz.io API skills, the agent can create and manage Open 360 and Cloud SIEM objects, such as alerts and dashboards, directly from the conversation. Find an error pattern worth watching? Ask the agent to create the alert. Need a view of a service you just investigated? Ask for the dashboard. The insight and the follow-through now happen in the same place.

AI agents are only as effective as the context they can access. The problem is that most of that context lives outside your observability platform.

OrionIQ’s agentic investigation is now built into Logz.io Open 360 AI. Ask a question and OrionIQ investigates across your telemetry, shows its work as it goes, links every finding back to the exact query behind it, and tells you how much to trust the answer. Today we’re bringing OrionIQ Chat into Open 360 AI. This is the first OrionIQ product to ship inside the Logz.io platform, and it’s the same agent that powers the standalone OrionIQ app, now available right where you already work.