> For the complete documentation index, see [llms.txt](https://docs.agentalk.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.agentalk.io/monitoring-and-analytics/review-call-history-and-logs.md).
# Review call history and logs
The call history gives you a complete record of every call your agents have handled. Use it to review conversations, investigate issues, and understand what happened in detail.
### Open call history
Start by accessing the list of all calls in your workspace.
Go to **Call history** from the sidebar.
### Filter the call history
Use filters to quickly find the calls you want to review.
At the top of the page, you’ll see the **Call Filters** section.
You can filter by:
* Call type
* Agent
* Date range
* Phone number or contact
Use these filters to narrow down specific calls or investigate a particular issue.
#### Filter by call status
Use the status tabs to switch instantly between all calls, answered calls, and missed calls.
1. Open **Call history** from the sidebar.
2. Look above the call list, below the main filter row.
3. Click one of the status tabs:
* **All Calls**
* **Answered**
* **Unanswered**
4. Wait for the list to refresh.
5. Review the new results from page 1.
Use **Answered** to review connected conversations. Use **Unanswered** to review missed calls that may need follow-up.
The selected tab combines with the rest of the page filters. For example, if you choose one agent and then click **Unanswered**, the list shows only missed calls for that agent.
If a filter combination returns no results, the empty state explains why. Clear the filter or switch tabs to broaden the list again.
### Review the call list
Below the filters, you’ll see the list of calls that match your criteria.
The list is shown in reverse chronological order.
Each row includes:
* Contact name and phone number
* Agent
* Call type
* Status
* Date and time
* Duration
Use this list to quickly scan recent activity and identify calls to review.
### Open a call record
Open a call to see full details about what happened during the conversation.
Click any call in the list.
By default, the call opens in the **Details** view.
#### Start with call details
The **Details** section gives you a quick overview of the call.
Here you can see:
* Contact information
* Call status
* Agent
* Call type
* Date and time
Use this as your starting point before diving deeper into the call.
#### Read the transcript
Read the full conversation between the agent and the caller.
The transcript is shown turn by turn, labeled by speaker. Use it to understand exactly what was said and where issues occurred.
#### Listen to the recording
Open the **Recording** tab to listen to the call audio.
Use this to understand tone, pauses, and how the conversation flowed.
{% hint style="info" %}
Call recordings may only be available on certain plans.
{% endhint %}
#### Review technical metrics
Open the **Technical metrics** tab to evaluate performance.
* **Latency**: Time between the caller finishing speaking and the agent responding.
* **Duration**: Total length of the call.
High latency may indicate a model or connection issue.
#### Use the log for debugging
Open the **Log** tab to see what happened step by step during the call.
Use this to:
* Understand how the agent executed the conversation.
* Debug unexpected behavior.
* Identify where something may have failed.
### Use error logs
If issues occur across multiple calls, use the **Error Log** to identify patterns.
Go to **Error Log** from the sidebar.
Here you can:
* View recent errors across your organization.
* Track how often errors occur.
* Identify recurring issues.
Each entry includes:
* Error status
* Timestamp
* Related activity
If no errors appear, your system is running without issues for the selected period.
### Diagnose issues step by step
Use this workflow when something in analytics or call behavior looks off.
1. Identify the issue (for example, short calls or low success rate).
2. Open a recent call for the affected agent.
3. Start in the **Details** tab to understand context.
4. Read the **Transcript.**
5. Listen to the **Recording.**
6. Check the **Log** for execution details.
7. Review **Technical metrics** if responses seem slow.
8. Check the **Error Log** for system-level issues.
This process helps you understand exactly what happened and why.
### Next steps
Here are the recommended next steps after completing this guide:
* [**Read the analytics dashboard**](/monitoring-and-analytics/read-the-analytics-dashboard.md): Identify trends and detect issues across all calls.
* [**Listen to and join live calls**](/monitoring-and-analytics/listen-to-and-join-live-calls.md): Observe calls in real time and intervene when needed.
---
# 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 dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:
```
GET https://docs.agentalk.io/monitoring-and-analytics/review-call-history-and-logs.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
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.