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

Who can see what in Observe?

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.

Runs & Traces

Can I rerun or edit an execution from Runs & Traces?

No. Runs & Traces is read-only. See Runs & Traces.

What's the difference between a thread, a run, a trace, and a span?

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.

How do I find a specific execution?

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.

Where do I see a model call's model, tokens, and cost?

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 and LLM Logs.

Analytics and logs

What does each Analytics tab show?

Overview: account-wide build activity. Apps: end-user engagement with published apps. Agents: agent execution volume, success rate, and quality. See Analytics.

What does Audit Trails record?

Configuration and access changes in the account, with the Actor, Module, and Action, most recent first. See Audit Trails.

Does Request Logs show all network traffic?

No. It records HTTP requests that pass through Qore: requests the platform receives, and requests it sends to external services. See Request Logs.

Are failed embedding calls logged?

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.

Export and Reports

What's the difference between Export and Reports?

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 and Reports.

Why did my export create several files?

Each dataset creates its own file. Selecting two datasets produces two files, not one merged workbook. See Choose data.

Which time zone do export schedules use?

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.

Can I download a report from the Reports page?

No. Read it as a table on the page, or have it emailed to you in PDF, CSV, or JSON. See Reports.

Troubleshooting

Runs & Traces

A trace shows "No traces to display"

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.

A run stays Waiting

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.

An ID looks cut short

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.

Analytics

The Agents tab shows a banner instead of data

The Agents tab needs Agent executor version 1.4 or above. On an older executor, the page shows a banner instead. See Agents.

Export and Reports

An export email or webhook didn't arrive

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.

I can't save an export

An export needs a name and at least one dataset. Webhook delivery also needs an HTTPS URL. See Plan an export.

I can't open Export, or Run now is disabled

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.

The export history is filtered to All projects again

Cancelling a new export returns the project filter to All projects. Choose the project again before reviewing history. See Track and update exports.

A report covers a different date range than I expected

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.

Related

• Runs & Traces, Analytics, Audit Trails, LLM Logs, Request Logs, DB Query Logs, Export, and Reports
• Monitor activity: every Observe task

---

Maintained by Abhishek Paul AI-assisted, human-approved