> For the complete documentation index, see [llms.txt](https://docs.uptiq.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.uptiq.ai/ai-workbench-qore/control-center/observe/observe-faqs-and-troubleshooting.md).

# Observe: FAQs & Troubleshooting

Answers to common Observe questions, and fixes for empty traces, waiting runs, and exports or reports that don't arrive.

This page answers common questions about Runs & Traces, Analytics, Audit Trails, the logs, Export, and Reports. Use the troubleshooting entries when a trace is empty, a run seems stuck, or a file doesn't arrive.

## FAQs

### Access

<details>

<summary>Who can see what in Observe?</summary>

**View traces**: every standard role except Viewer. **View analytics**, **View audit logs**, and **View reports**: Governance Manager, Auditor, Account Admin, and Organisation Admin. **Run exports**: the same four roles; **Manage exports**: Governance Manager, Account Admin, and Organisation Admin. See [Roles](/ai-workbench-qore/control-center/admin/roles.md).

</details>

### Runs & Traces

<details>

<summary>Can I rerun or edit an execution from Runs &#x26; Traces?</summary>

No. Runs & Traces is read-only. See [Runs & Traces](/ai-workbench-qore/control-center/observe/runs-and-traces.md).

</details>

<details>

<summary>What's the difference between a thread, a run, a trace, and a span?</summary>

A **thread** is the conversation or session; it can hold several **runs**, each one agent or app execution. A **trace** is the ordered record of one run, and a **span** is one step in it, such as an LLM call or a tool call. See [Concepts](/ai-workbench-qore/control-center/observe/runs-and-traces.md#concepts).

</details>

<details>

<summary>How do I find a specific execution?</summary>

Search by its full thread or execution ID, or by agent, project, business ID, or date range. Criteria combine, so only runs matching all of them appear. See [Find an execution](/ai-workbench-qore/control-center/observe/runs-and-traces.md#find-an-execution).

</details>

<details>

<summary>Where do I see a model call's model, tokens, and cost?</summary>

Open its `LlmGeneration` span in the trace: LLM spans report the model, provider, input and output tokens, credits, and USD cost. Across all calls, use **LLM Logs** › **Gateway Logs**. See [Inspect a trace](/ai-workbench-qore/control-center/observe/runs-and-traces.md#inspect-a-trace) and [LLM Logs](/ai-workbench-qore/control-center/observe/llm-logs.md).

</details>

### Analytics and logs

<details>

<summary>What does each Analytics tab show?</summary>

**Overview**: account-wide build activity. **Apps**: end-user engagement with published apps. **Agents**: agent execution volume, success rate, and quality. See [Analytics](/ai-workbench-qore/control-center/observe/analytics.md).

</details>

<details>

<summary>What does Audit Trails record?</summary>

Configuration and access changes in the account, with the **Actor**, **Module**, and **Action**, most recent first. See [Audit Trails](/ai-workbench-qore/control-center/observe/audit-trails.md).

</details>

<details>

<summary>Does Request Logs show all network traffic?</summary>

No. It records HTTP requests that pass through Qore: requests the platform receives, and requests it sends to external services. See [Request Logs](/ai-workbench-qore/control-center/observe/request-logs.md).

</details>

<details>

<summary>Are failed embedding calls logged?</summary>

Yes. **Embedding Logs** records every query sent to an embedding model, from any provider and any part of the platform, including calls that fail. See [Embedding Logs](/ai-workbench-qore/control-center/observe/llm-logs.md#embedding-logs).

</details>

### Export and Reports

<details>

<summary>What's the difference between Export and Reports?</summary>

**Export** delivers datasets as files by email or webhook, once or on a schedule. **Reports** are fixed templates, the Credit Usage Report and the Agent Executions Report, that you read in the platform or receive by email; they can't run on a schedule. See [Export](/ai-workbench-qore/control-center/observe/export.md) and [Reports](/ai-workbench-qore/control-center/observe/reports.md).

</details>

<details>

<summary>Why did my export create several files?</summary>

Each dataset creates its own file. Selecting two datasets produces two files, not one merged workbook. See [Choose data](/ai-workbench-qore/control-center/observe/export.md#choose-data).

</details>

<details>

<summary>Which time zone do export schedules use?</summary>

UTC. The default schedule is daily at `02:00` UTC; weekly runs start on Monday and monthly runs on the first day of the month, and those anchors can't be changed. See [Schedule delivery](/ai-workbench-qore/control-center/observe/export.md#schedule-delivery).

</details>

<details>

<summary>Can I download a report from the Reports page?</summary>

No. Read it as a table on the page, or have it emailed to you in PDF, CSV, or JSON. See [Reports](/ai-workbench-qore/control-center/observe/reports.md#choose-report-details).

</details>

## Troubleshooting

### Runs & Traces

<details>

<summary>A trace shows "No traces to display"</summary>

The logs couldn't reconstruct spans. That's normal for short, aborted, or incompletely logged runs, and doesn't mean the run failed. See [Inspect a trace](/ai-workbench-qore/control-center/observe/runs-and-traces.md#inspect-a-trace).

</details>

<details>

<summary>A run stays Waiting</summary>

**Waiting** covers both a run that's executing and one paused on an external step, such as an item awaiting Human Review. Check Human Review before treating it as stuck, and refresh the results. See [Status values](/ai-workbench-qore/control-center/observe/runs-and-traces.md#status-values).

</details>

<details>

<summary>An ID looks cut short</summary>

IDs can be shortened for readability. Point to an ID to see the full value, and copy the full trace ID from its details. See [Find an execution](/ai-workbench-qore/control-center/observe/runs-and-traces.md#find-an-execution).

</details>

### Analytics

<details>

<summary>The Agents tab shows a banner instead of data</summary>

The Agents tab needs **Agent executor version 1.4 or above**. On an older executor, the page shows a banner instead. See [Agents](/ai-workbench-qore/control-center/observe/analytics.md#agents).

</details>

### Export and Reports

<details>

<summary>An export email or webhook didn't arrive</summary>

Get the file from the completed-run history while its download link is still valid, and refresh the history for the latest state. With no recipients entered, the link goes to your own signed-in account. See [Track and update exports](/ai-workbench-qore/control-center/observe/export.md#track-and-update-exports).

</details>

<details>

<summary>I can't save an export</summary>

An export needs a name and at least one dataset. Webhook delivery also needs an HTTPS URL. See [Plan an export](/ai-workbench-qore/control-center/observe/export.md#plan-an-export).

</details>

<details>

<summary>I can't open Export, or Run now is disabled</summary>

The **Export** page needs the **Manage exports** capability: Governance Manager, Account Admin, or Organisation Admin. **Run now** on a saved export needs **Run exports**; without it, hovering shows *You don't have access to run exports*. See [Roles](/ai-workbench-qore/control-center/admin/roles.md).

</details>

<details>

<summary>The export history is filtered to All projects again</summary>

Cancelling a new export returns the project filter to `All projects`. Choose the project again before reviewing history. See [Track and update exports](/ai-workbench-qore/control-center/observe/export.md#track-and-update-exports).

</details>

<details>

<summary>A report covers a different date range than I expected</summary>

The starting date range can change after you use another report, and ranges use calendar dates, not wall-clock times. Set the range again, with exact dates when your work crosses UTC midnight. See [Choose report details](/ai-workbench-qore/control-center/observe/reports.md#choose-report-details).

</details>

### Related

* [Runs & Traces](/ai-workbench-qore/control-center/observe/runs-and-traces.md), [Analytics](/ai-workbench-qore/control-center/observe/analytics.md), [Audit Trails](/ai-workbench-qore/control-center/observe/audit-trails.md), [LLM Logs](/ai-workbench-qore/control-center/observe/llm-logs.md), [Request Logs](/ai-workbench-qore/control-center/observe/request-logs.md), [DB Query Logs](/ai-workbench-qore/control-center/observe/db-query-logs.md), [Export](/ai-workbench-qore/control-center/observe/export.md), and [Reports](/ai-workbench-qore/control-center/observe/reports.md)
* [Monitor activity](/ai-workbench-qore/task-guides/monitor-activity.md): every Observe task

***

{% columns %}
{% column width="83.33333333333334%" %}

<p align="right"><em>Maintained by</em> <mark style="color:green;">Abhishek Paul</mark><br><code>AI-assisted, human-approved</code></p>
{% endcolumn %}

{% column width="16.666666666666664%" %}

<div align="left"><img src="https://1326225582-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F0qmgQjJ5aArDTj2ACFHG%2Fuploads%2Fgit-blob-d034645b4f8f8ee661985f5306b60ded3289653c%2Fmaintainer-abhishek-paul.png?alt=media" alt="" width="60"></div>
{% endcolumn %}
{% endcolumns %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.uptiq.ai/ai-workbench-qore/control-center/observe/observe-faqs-and-troubleshooting.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.