{"slug": "introducing-ai-observability-debug-agents-with-full-app-and-infra-context", "title": "Introducing AI Observability: Debug Agents with Full App and Infra Context", "summary": "SigNoz launched AI Observability in SigNoz Cloud, an OpenTelemetry-native product that tracks agent runs and LLM signals alongside logs, services and infrastructure. The release adds an AI Observability dashboard for token usage, cost, latency, errors and tool calls, a thread view showing a full agent run as a conversation, correlated debugging across services and infra metrics, an LLM-aware trace view, attribute mapping to OpenTelemetry GenAI conventions (gen_ai.*), and custom model pricing with costs updated daily from OpenRouter. SigNoz cites Gartner's projection that 40% of enterprise applications will include task-specific AI agents by the end of 2026, up from less than 5% in 2025.", "body_md": "# Introducing AI Observability: Debug Agents with Full App and Infra Context\n\n## TL;DR\n\nAI Observability is live in SigNoz Cloud. It’s OpenTelemetry-native. You can now track your agent runs and LLM signals next to your logs, services and infrastructure. Here are the highlights:\n\n- AI Observability dashboard: track a new class of LLM signals, like token usage, cost, latency, errors and tool calls.\n- Thread view: see a complete agent run as a conversation, with the input and output messages at each step.\n- Correlated debugging: connect LLM signals with your services, logs, databases and infra metrics to debug agents across the whole workflow.\n- LLM-aware trace view: LLM calls are labeled in the trace, and the span card shows input and output messages and token usage up front.\n- Attribute mapping: map your existing instrumentation, from any framework or model provider, to the OpenTelemetry GenAI conventions (`gen_ai.*` ).\n- Custom model pricing: model costs update daily from OpenRouter, and you get an option to set your own.\n\nOur applications are changing. It’s no longer services calling other services. We are embedding more and more agents and LLM calls inside our application workflows.\n\nGartner expects 40% of enterprise applications to include task-specific AI agents by the end of 2026, up from less than 5% in 2025. By 2028, it expects a third of user experiences to shift from native apps to agentic front ends ([Gartner](https://gartner.com/en/newsroom/press-releases/2025-08-26-gartner-predicts-40-percent-of-enterprise-apps-will-feature-task-specific-ai-agents-by-2026-up-from-less-than-5-percent-in-2025)).\n\nAt its core, observability is seeing your entire system, every request, every service, every hop, through the data it already emits.\n\nWith agents in the loop, what “the system” is, and how a request flows, looks radically different. As software changes, observability will shift with it. That’s where AI observability comes in.\n\nWe need a unified portal, not multiple portals… where my logs, traces, and metrics are covered. It's not only logs and all, AI observability is also one part…And I want all this in one place. - E2E Networks\n\n## How AI agents are changing observability: 4 key shifts\n\n1. \nLLM calls are non-deterministic and come at a cost. For the same request, you may get 2 different answers, 2 different paths to answer, and 2 different set of tool calls. Plus, LLM calls bring their own class of signals. In [LLM monitoring](https://signoz.io/docs/llm-observability-core-concepts/) , you need to track token usage, cost, errors, models, tool calls, and latency. You also need to evaluate the agent’s reasoning, using the input and output messages and quality checks.\n2. \nAgentic workflows turn traces from lines into trees. A traditional trace is a single chain - API, service, database. An agent breaks that shape. One agent call spreads into parallel lines of LLM calls, tool calls, sub-agents, and more. That brings new debugging questions. Is the agent stuck in a loop? Is it taking the right path to the answer? This is making us rethink how to interact with traces.\n3. \nAgents write the code. Production becomes the final review. Google says about 75% of its new code is now AI-generated, up from about 25% in October 2024 ( [TechSpot](https://www.techspot.com/news/112152-google-ai-now-generates-75-new-code-up.html) ). As agents write more of our code, the volume of code is exploding.No team can read and review all of it. Production becomes the final test. Observability’s job expands from keeping systems running to checking whether the code is working as intended.\n4. \nObservability is the feedback signal in the loop. Building on the previous point, software development is heading toward a loop: agents write code, review it, test it, ship it, and monitor it. On top of that, there are agents running inside the application, serving users. This loop needs a feedback signal to improve. Observability is that signal, bringing real production insight back to the humans and agents in the loop.\n\nAI Observability is our first big step on this path.\n\n## AI Observability in SigNoz Cloud\n\nWe’re launching AI observability in SigNoz Cloud. Monitor your agent runs and LLM calls alongside your logs, services and infrastructure.\n\nAI observability can’t live on a separate platform, siloed from the rest of your application and infrastructure data. When you debug an agent, the issue may be in the agent itself, or outside it. It could be a tool, a database or the infrastructure underneath.\n\nWe’ve heard from teams who hop between an AI observability tool and SigNoz Cloud or another observability platform, lining up timestamps by hand to piece one request back together.\n\nWith SigNoz Cloud, all your LLM signals sit right next to your logs, services and infrastructure. No more tab-hopping. And of course 😉, it’s OpenTelemetry-native - no vendor lock-in, no proprietary SDK, and it works with any framework.\n\n## Key features of SigNoz Cloud AI Observability\n\n### AI Observability Dashboard to track all your LLM signals\n\nYou’ll find a new AI Observability section in the left navigation. It opens a ready-made dashboard that tracks every LLM and agent signal.\n\nIt includes charts for,\n\n- Token usage - tokens split into input, output and cached.\n- Cost - total spend and cost over time.\n- Latency - p50 to p99 latency per model for every inference request, plus time to first token.\n- Errors - grouped by type, like rate limit, timeout and auth.\n- Tool calls - call rate, error rate and duration for each tool.\n\nYou can filter every chart by model, provider, environment or service.\n\nSee the [telemetry requirements](https://signoz.io/docs/ai-observability-telemetry-requirements/) for the attributes each panel needs.\n\nThe [Explorer tab](https://signoz.io/docs/ai-observability-explorer/) also lists every AI trace in your system. Each trace gets roll-up totals for tool calls, tokens, cost and more, like `trace.total_tokens`.\n\nYou see these totals next to each trace in the Explorer table. Use the same fields in your queries and filters. For example, find every trace over 10K tokens.\n\n### End-to-end agent tracing with LLM-aware spans\n\nWe’ve updated the trace view and span card to make LLM calls and AI workloads easier to read.\n\nFirst, as all your signals are in one place, you can see the complete trace. Trace a request from your web app, through your backend, into the inference service, and see exactly where it slowed down or failed.\n\nThe SigNoz Cloud trace view already supports [unlimited spans](https://signoz.io/blog/new-trace-detail-view/), so large AI traces load in full, with no span limits. The LLM filter isolates every LLM call in even the densest trace.\n\nFrom LLM spans, you can jump to logs and infra around them.\n\nOn top of that, we’ve added:\n\n- **AI span labels:** All AI spans get a label, so they stand out in the waterfall.\n- **Input and output messages:** the span card for an LLM call shows what went into the model and its response.\n- **Token usage and cost up front:** both sit at the top of the span card for every LLM call.\n\n### Follow agent reasoning step by step in the new thread view\n\nThe new thread view in trace details shows an AI trace as a conversation, so you can follow what an agent did at each step.\n\nAs we covered earlier, AI workflows are breaking the shape of a trace. The waterfall shows each step and when each span ran, but it doesn’t show the messages behind them.\n\nThe thread view lays out the full exchange in order:\n\n- **System prompt:** the instructions the agent started with.\n- **Inputs and outputs:** each message sent to the model and what it returned.\n- **Tool calls:** each tool the agent called, with the arguments and the response it got back.\n\nFor example, a user asks your customer support agent to cancel their subscription, but the agent ends up pitching a discount. With each input and output in sequence, you can see exactly where the agent drifted off course.\n\nIn trace details, open the **Thread** tab next to **Overview**. When you open a trace from AI Observability, you land on the Thread tab directly.\n\n### Correlate LLM signals with your services, logs and infra\n\nNot every agent failure starts in the agent or the LLM. It could be an overloaded pod, a slow database, a downstream endpoint that hangs, or the inference service itself.\n\nSigNoz Cloud already has your application, service and infrastructure data. With AI Observability, your LLM and agent signals live in the same place, so you see the complete workflow your agents run in and the infrastructure they run on.\n\nThat means you can answer questions that span your agent runs, LLM signals, app and infra in one platform:\n\n- Is my agent slow because of the inference service, or the storage or the pods behind it?\n- Did these LLM timeouts start when the pods restarted?\n- Which endpoint or customer is driving our token spend?\n\n**Set up dashboards and alerts on correlated signals.** Put LLM latency next to pod CPU and memory, or alert when the pods behind your agent service start restarting, so you know before your agents fail.\n\n### Instrument any framework with attribute mapping\n\nSigNoz Cloud AI Observability is built on the OpenTelemetry GenAI semantic conventions. It works with [any framework](https://signoz.io/docs/llm-observability/) that emits OTLP traces, with no SigNoz SDK or proprietary agent in your app.\n\nHowever, not every library uses the same attribute names. OpenInference, custom SDKs and different model providers each follow their own conventions.\n\nSo we’ve added [Attribute Mapping](https://signoz.io/docs/ai-observability-attribute-mapping/), which lets you keep your existing instrumentation and map its fields to the OpenTelemetry GenAI conventions (`gen_ai.*`). Once mapped, those fields power the dashboard, queries and alerts.\n\n- **Easily portable.** Because everything is built on standard`gen_ai.*` fields, you can switch frameworks or add a new provider with minimal changes.\n- **Mappings run on ingest.** Each mapping has one target`gen_ai.*` attribute and a list of source attributes in priority order. For each span, SigNoz takes the first source that exists and writes it to the target. If the span already has the target, SigNoz leaves it alone.\n- **Defaults cover common libraries** . SigNoz ships default mappings for common LLM libraries, and you can add your own groups, scoped by conditions, for in-house instrumentation.\n\n### Set your own model pricing\n\nSigNoz Cloud calculates the cost of every LLM call for you. It reads the input, output and cached token counts on each span. Then it applies the model’s price and writes the cost back to the span as `signoz.gen_ai.usage.tokens.cost`.\n\nPrices for known models are filled in automatically. SigNoz Cloud updates them daily from [OpenRouter](https://openrouter.ai/). New models and price changes are picked up without any manual effort.\n\nSet custom prices when the defaults don’t fit. You may be using a model with no public price, like a fine-tuned or self-hosted one. Or you may have negotiated a better rate with your provider.\n\nIn the [Model pricing tab](https://signoz.io/docs/ai-observability-model-pricing/), set your own price per million tokens. Your cost dashboards, queries and alerts use it from then on.\n\n## Availability\n\nAI Observability is available on SigNoz Cloud and self-hosted SigNoz. Self-hosted users with a custom collector config need to add the `signozspanmapper` and `signozllmpricing` processors to the traces pipeline. The earlier `/llm-observability/*` routes are now `/ai-observability/*`.\n\n## What’s next in AI Observability - Session View\n\nMost of the agent workflows spans over multiple traces. So, we're building a session view that strings every trace in a conversation together, so you can follow the complete chain of agent worklow across the whole session.\n\n## Get started with SigNoz AI Observability\n\nSigNoz is OpenTelemetry-native, with traces, logs, metrics and now your agents in one place. See every agent run alongside the services and infrastructure it runs on.\n\nStart with [SigNoz Cloud](https://signoz.io/teams/) and get 30 days of unrestricted access to every feature. To send your first LLM traces, follow the [AI Observability docs](https://signoz.io/docs/ai-observability/).\n\nYou can also run SigNoz as a [self-hosted Enterprise edition](https://signoz.io/contact-us/) or the open-source [Community edition](https://signoz.io/docs/install/self-host/).", "url": "https://wpnews.pro/news/introducing-ai-observability-debug-agents-with-full-app-and-infra-context", "canonical_source": "https://signoz.io/blog/introducing-ai-observability", "published_at": "2026-11-16 00:00:00+00:00", "updated_at": "2026-11-17 20:05:43.322946+00:00", "lang": "en", "topics": ["ai-agents", "mlops", "ai-tools", "large-language-models"], "entities": ["SigNoz", "SigNoz Cloud", "OpenTelemetry", "OpenRouter", "Gartner", "Google", "E2E Networks"], "also_reported_by": [], "takeaway": "SigNoz's AI Observability maps existing instrumentation from any framework or model provider to OpenTelemetry GenAI gen_ai.* conventions, letting teams view token usage, cost, latency, errors and tool calls in the same traces as their services and infra.", "recommendation": null, "alternates": {"html": "https://wpnews.pro/news/introducing-ai-observability-debug-agents-with-full-app-and-infra-context", "markdown": "https://wpnews.pro/news/introducing-ai-observability-debug-agents-with-full-app-and-infra-context.md", "text": "https://wpnews.pro/news/introducing-ai-observability-debug-agents-with-full-app-and-infra-context.txt", "jsonld": "https://wpnews.pro/news/introducing-ai-observability-debug-agents-with-full-app-and-infra-context.jsonld"}}