---
title: "Monitoring Candela AI activity"
slug: "monitoring-candela-ai-activity"
updated: 2026-04-27T09:32:00Z
published: 2026-04-27T09:32:00Z
canonical: "support.lusid.com/monitoring-candela-ai-activity"
---

> ## Documentation Index
> Fetch the complete documentation index at: https://support.lusid.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Monitoring Candela AI activity

Candela tracks every conversation as a trace, giving you visibility into what happened, when, and why. You can retrieve and review the full event log for any conversation to help you:

- Review what Candela did on behalf of yourself or another user
- Diagnose unexpected behaviour
- Satisfy audit requirements

## How conversation tracking works

Each Candela conversation is recorded as a trace. A trace captures the complete sequence of events in a conversation, including every:

- Message you send
- Tool the [agent](/v1/docs/understanding-candela-s-system-agents) calls
- Result the agent receives
- Agent transition that occurs

> [!NOTE]
> Confirming write operations
> 
> Candela distinguishes between read operations, write operations, and destructive operations.
> 
> 
> 
> Before executing a destructive action such as deleting a file from LUSID Drive, Candela always asks you to confirm. This confirmation step is recorded in the trace alongside the your response, providing a clear audit record of user intent.

## Viewing traces

Provided you have administrator privileges, you can view traces via the web app or [retrieve them programmatically](/v1/docs/monitoring-candela-ai-activity#retrieving-traces-via-api) via the Candela API.

Navigate to **Insights > AI Assistant Traces** to view all conversation traces for a given time period, and retrieve the trace ID for a particular conversation:

![](https://cdn.document360.io/d575ad81-c0ed-4980-bbd1-d59ac5c3de82/Images/Documentation/image-5S2D3KL8.png?sv=2026-02-06&spr=https&st=2026-11-09T06%3A42%3A12Z&se=2026-11-09T07%3A42%3A12Z&sr=c&sp=r&sig=XjGuhS2vDKLyiunLuNwhsavs%2FME0wJ%2FxpZcaK5OJWxY%3D)

### Viewing the trace for a particular conversation

Select the **View** icon on any trace to open the full details of a conversation: ![](https://cdn.document360.io/d575ad81-c0ed-4980-bbd1-d59ac5c3de82/Images/Documentation/image-ANOY7ONS.png?sv=2026-02-06&spr=https&st=2026-11-09T06%3A42%3A12Z&se=2026-11-09T07%3A42%3A12Z&sr=c&sp=r&sig=XjGuhS2vDKLyiunLuNwhsavs%2FME0wJ%2FxpZcaK5OJWxY%3D)

Each trace includes:

- The complete event log, showing every message, tool call, tool result, and agent transition
- A diagram of the agent workflow for the conversation
- A search bar for navigating the event log
- A link to the correlated [request logs](/v1/docs/tracking-and-grouping-api-calls-using-correlation-ids)

![](https://cdn.document360.io/d575ad81-c0ed-4980-bbd1-d59ac5c3de82/Images/Documentation/image-52FMP072.png?sv=2026-02-06&spr=https&st=2026-11-09T06%3A42%3A12Z&se=2026-11-09T07%3A42%3A12Z&sr=c&sp=r&sig=XjGuhS2vDKLyiunLuNwhsavs%2FME0wJ%2FxpZcaK5OJWxY%3D)

### Retrieving traces via API

You can also retrieve traces programmatically via the [CandelaTraces API](https://www.lusid.com/docs/api/insights/endpoints/candela-traces/ListTraceLogs), which is useful for building audit reports or integrating trace data into your external tools.

For example, to list all traces:

```shell
curl -X GET "https://<your-domain>.lusid.com/insights/api/candelatraces"
   -H "Authorization: Bearer <your-API-access-token>"
```