{"slug": "ai-observability-explorer-query-llm-ai-trace-data", "title": "AI Observability Explorer - Query LLM & AI Trace Data", "summary": "SigNoz documented the Explorer tab of its AI Observability product, a query interface where users write filters on LLM and AI trace data and view results in four views: Trace View, List View, Time Series, and Table. The Explorer supports trace-level fields such as trace.total_tokens, trace.estimated_total_cost, and trace.llm_call_count, and offers seven quick-filter fields including deployment.environment, gen_ai.provider.name, and gen_ai.agent.name. Trace View uses all spans of each trace, including spans outside the selected time range, while List View, Time Series, and Table use only spans inside the selected time range.", "body_md": "The **Explorer** is the query tab of [AI Observability](https://signoz.io/docs/ai-observability/). The **Overview** tab shows a fixed dashboard. In the Explorer, you write your own queries on LLM and AI trace data and pick one of four views for the results.\n\nUse this page to run a query, filter it, pick a view, and open a trace.\n\n## Open the Explorer\n\n1. In the side navigation, open the **More** menu and select**AI Observability** .\n2. In the tab bar at the top, select **Explorer** .\n\nAll roles (Admin, Editor, and Viewer) can use the Explorer.\n\n## Run a query\n\n1. Type a filter in the filter bar, for example `trace.total_tokens > 1000` .\n2. Select **Run Query** , or press Cmd+Enter (Ctrl+Enter on Windows and Linux).\n\nFields with the `trace.` prefix hold the totals of a trace, such as `trace.total_tokens`, `trace.estimated_total_cost`, and `trace.llm_call_count`. You can filter and aggregate on these fields, which the Trace Explorer does not have.\n\nThe filter bar suggests only keys and values from GenAI spans. After you add a filter, the next suggestions show only values that match your current filters. For the filter syntax and the aggregation options, see [Query Builder](https://signoz.io/docs/userguide/query-builder-v5/).\n\nWhile a query runs, the **Run Query** button changes to **Cancel**. If you select **Cancel**, the view is empty until you run the query again.\n\nTo run the query again at an interval, turn on auto-refresh in the time picker.\n\n## Quick filters\n\nUse the quick filters panel on the left to filter by common fields without typing a query. The panel has seven fields:\n\n- `deployment.environment`\n- `gen_ai.operation.name`\n- `gen_ai.provider.name`\n- `gen_ai.request.model`\n- `service.name`\n- `gen_ai.tool.name`\n- `gen_ai.agent.name`\n\nEach field lists **RELATED** values first. These values match the filters that you already applied. **ALL VALUES** lists the rest. When you select a value, the query changes and the active view shows the new results. To hide the panel, use the control at the top of the panel. To show it again, select **Show Filters** in the toolbar.\n\n## Views\n\nThe toolbar has four views: **Trace View**, **List View**, **Time Series**, and **Table**. All views use the same query. The Explorer opens in **Trace View**.\n\nFor trace totals, the views use different spans:\n\n- **Trace View** uses all the spans of each trace, also the spans outside the selected time range.\n- **List View** ,**Time Series** , and**Table** use only the spans of each trace inside the selected time range. For example, with the filter`trace.total_tokens > 100` , SigNoz adds up the tokens of the spans of that trace in the time range.\n\n### Trace View\n\n**Trace View** shows one row for each AI trace, with totals for the trace such as tokens, cost, and call counts. To open the full trace, select a row. To open it in a new tab, hold Cmd (Ctrl on Windows and Linux) and select the row.\n\nThe trace opens in [Trace Details](https://signoz.io/docs/userguide/span-details/). To show only the LLM spans of the trace, select the **LLM** [quick filter](https://signoz.io/docs/userguide/span-details/#quick-filters) at the top of that page.\n\nThe columns come from the trace fields that SigNoz finds for your data. By default, the table shows each of these fields that exists, in this order:\n\n`trace_id`, `service.name`, `root_span_name`, `estimated_total_cost`, `trace_duration_nano`, `span_count`, `total_tokens`, `input_tokens`, `output_tokens`, `distinct_tool_count`, `llm_call_count`, `tool_call_count`, `start_time`, `end_time`, `error_count`, `input`, `output`, `max_llm_duration_nano`\n\nUse the two controls above the table:\n\n- **Order by** : sort the traces by a trace field, in ascending or descending order. The default is`last_activity_time (desc)` . You can sort by fields that the table does not show as columns, such as`last_activity_time` .\n- **Options** : open the**Edit columns** drawer to show, hide, or reorder columns.\n\nYou cannot hide or remove the `trace_id` column, but you can drag it to a different position. Your browser saves your column selection, so the selection applies only in that browser.\n\n### List View\n\n**List View** shows one row for each span. The default columns are `timestamp`, `service.name`, `name`, `duration_nano`, `http_method`, and `response_status_code`. The newest spans are at the top.\n\nTo change the columns:\n\n- To remove a column, open the column actions in its header and select **Remove column** .\n- To reorder a column, drag its header.\n- To resize a column, drag the edge of its header.\n\nThe `timestamp` column stays first. Your browser saves your column changes. To open the trace of a span, select its row.\n\n### Time Series\n\n**Time Series** shows the query results as a chart over time. If every query aggregates the span duration, the Y-axis unit is milliseconds. Otherwise, the unit is a plain number. To change the unit, use the unit control of the chart. You can also export the chart data.\n\nTo see exact cost values, use the **Table** view.\n\n### Table\n\n**Table** shows the aggregated results of the query in a grid. To download the results, select the download icon, select **csv** or **jsonl** as the format, and then select **Export**.\n\n## Common tasks\n\n| Task | Steps | \n|---|---|\n| Find the most expensive traces | In **Trace View** , set**Order by** to`estimated_total_cost (desc)` . | \n| Find failed tool calls | In **List View** , run the filter`gen_ai.tool.name EXISTS AND has_error = true` . | \n| Chart token usage by model | In **Time Series** , set the aggregation to`sum(gen_ai.usage.input_tokens)` and group by`gen_ai.request.model` . | \n| Compare cost by model | In **Table** , set the aggregation to`sum(signoz.gen_ai.usage.tokens.cost)` and group by`gen_ai.request.model` . The**Cost over time** panel on the[Overview dashboard](https://signoz.io/docs/ai-observability/) charts the same query. | \n\n## Related\n\n- [AI Observability overview](https://signoz.io/docs/ai-observability/) : the Overview dashboard and the attributes that it needs.\n- [Trace Details](https://signoz.io/docs/userguide/span-details/) : inspect the spans of one trace.\n- [Attribute Mapping](https://signoz.io/docs/ai-observability-attribute-mapping/) : map non-standard attributes to GenAI names.\n- [LLM Observability integrations](https://signoz.io/docs/llm-observability/) : instrument OpenAI, Anthropic, LiteLLM, CrewAI, and other frameworks.\n\n## Get Help\n\nIf you need help with the steps in this topic, please reach out to us on [SigNoz Community Slack](https://signoz.io/slack/). If you are a SigNoz Cloud user, please use in product chat support located at the bottom right corner of your SigNoz instance or contact us at [cloud-support@signoz.io](mailto:cloud-support@signoz.io).", "url": "https://wpnews.pro/news/ai-observability-explorer-query-llm-ai-trace-data", "canonical_source": "https://signoz.io/docs/ai-observability-explorer", "published_at": "2026-09-29 00:00:00+00:00", "updated_at": "2026-09-29 12:48:44.195312+00:00", "lang": "en", "topics": ["ai-tools", "mlops", "large-language-models", "ai-agents"], "entities": ["SigNoz", "AI Observability", "Explorer", "Trace View", "List View", "Time Series", "Table"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/ai-observability-explorer-query-llm-ai-trace-data", "markdown": "https://wpnews.pro/news/ai-observability-explorer-query-llm-ai-trace-data.md", "text": "https://wpnews.pro/news/ai-observability-explorer-query-llm-ai-trace-data.txt", "jsonld": "https://wpnews.pro/news/ai-observability-explorer-query-llm-ai-trace-data.jsonld"}}