# Call Recordings

Every call handled by the AI Voice Agent is recorded and transcribed automatically. You can listen to recordings, read transcripts, and review what actions the AI took -- all from one screen.

## How It Works

1. **Open the call list.** Go to the Voice Agent section and click on the call log.
2. **Find the call you want.** Calls are listed by date with the caller's phone number, a short summary, and the call duration. Use the search bar or date filter to narrow things down.
3. **Click a call to open it.** You'll see:
   * **Recording** -- press play to listen to the full conversation
   * **Transcript** -- a written version of the entire call, showing who said what
   * **Actions taken** -- any appointments booked, messages flagged, or questions answered
   * **Call details** -- date, time, duration, and caller phone number
4. **Review and follow up.** If the AI flagged something for follow-up, you can take action right from the call detail screen.

## Why This Matters

* **Quality check.** Make sure the AI is handling calls the way you want.
* **Resolve disputes.** If a customer says "that's not what I was told," you have the recording.
* **Train the AI.** If you notice the AI struggling with certain questions, add that information to your knowledge base.

***

**Related Pages**

* [How Calls Work](/ai-voice-agent-and-dispatch/proforge-csr/voice-agent/how-calls-work.md)
* [Booking Appointments](/ai-voice-agent-and-dispatch/proforge-csr/voice-agent/booking-appointments.md)
* [Knowledge Base Setup](/ai-voice-agent-and-dispatch/proforge-csr/csr-settings/knowledge-base.md)


---

# Agent Instructions: Querying This Documentation

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

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.proforgeerp.com/ai-voice-agent-and-dispatch/proforge-csr/voice-agent/call-recordings.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.