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

# Logs

> Find failed production conversations and see why.

![The Logs page with one row for each production conversation, showing its date and time, agent, status, and duration](https://mintcdn.com/bluejay/eKcFBkjZX47pI8Ss/images/logs-page.png?fit=max\&auto=format\&n=eKcFBkjZX47pI8Ss\&q=85\&s=be9d4c04e1b24ba4906b71bc19444b04)

## Get conversations into Logs

Logs shows your production conversations. They can arrive from three sources:

| Source | How conversations arrive |
| - | - |
| Voice platform | Each ended call arrives after you [connect the platform](/integrations/vapi.md#monitor). |
| [`POST /v1/evaluate`](/api-reference/endpoint/evaluate) | Your backend sends each conversation after it ends. |
| **Upload** | Upload **Audio Call** files or a **Chat/Transcript** from the Logs page. |

## Find a conversation

To find the conversations worth reading, start from a failing metric or an issue, then read the transcript to see where the agent went wrong. You can also type a plain-text query in the search box, for example "failed calls yesterday". If a transcript does not explain the failure, open the linked [Traces](/monitor/traces.md).

## Act on conversations

You can also run these options on any selected conversations:

* **Reevaluate** runs the metrics again on up to 100 conversations at a time. If all selected conversations belong to one agent, it can use a different agent version, so you can check a fix on real conversations.
* **Replay** tests the conversations against a target agent in a [simulation](/test/simulations/create.md), so a real failure becomes a repeatable test.
* **Metrics Lab** puts the conversations in a new or existing [Metrics Lab](/monitor/metrics.md#metrics-lab). Use it when a metric verdict looks wrong on many conversations.

## Related

* [Evaluate API](/api-reference/endpoint/evaluate.md)
* [Monitoring MCP tools](/mcp/monitoring-tools.md#monitor)
* [Tool Calls, Events, and Metadata](/monitor/metrics.md#tool-calls-events-and-metadata)
* [Traces](/monitor/traces.md)
* [Issues](/monitor/issues.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.