> For the complete documentation index, see [llms.txt](https://docs.maiagent.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.maiagent.ai/maiagent-user-guide/maiagent-user-guide-en/conversations/inbox-search.md).

# Inbox Search

### Overview

The inbox search feature lets you quickly find specific conversation records without manually scrolling through a long conversation list. Using keyword search, you can instantly filter relevant conversations, significantly improving customer service efficiency.

{% hint style="info" %}
This feature supports instant search (search as you type) and automatically saves recent search history for quick repeat queries.
{% endhint %}

***

### How to Use the Search Feature

#### Basic Search

1. **Go to the inbox page**
   * Click "<mark style="color:blue;">Customer Service</mark>" in the left menu
   * Click "<mark style="color:blue;">All Conversations</mark>" or select a specific chat platform
2. **Enter search keywords**
   * Type keywords in the search box above the inbox
   * The system instantly displays matching conversations
3. **View search results**
   * The conversation list automatically filters to show only conversations containing the keywords
   * Matching keywords are highlighted

#### Search Scope

The system searches the following fields:

* Conversation content (user messages and AI replies)
* Username
* Conversation title (if set)
* Contact information (if integrated)

{% hint style="warning" %}
The search feature can only search conversations within the currently displayed inbox (e.g., LINE, Facebook, Web Chat, etc.). For cross-platform searches, use the "All Conversations" page.
{% endhint %}

***

### Advanced Search Tips

#### Using Filter Conditions

In addition to keyword search, you can combine the following filter conditions:

1. **Time range**
   * Today's conversations
   * Last 7 days
   * Last 30 days
   * Custom date range
2. **Conversation status**
   * In progress
   * Ended
   * Pending
3. **AI Assistant**
   * Select conversations from a specific AI Assistant

#### Search Combination Examples

**Example 1: Search for recent return-related conversations**

```
Search keyword: Return
Time range: Last 7 days
Conversation status: All
```

**Example 2: Search for a specific customer's conversation history**

```
Search keyword: John Smith
Time range: Last 30 days
AI Assistant: Customer Service AI
```

***

### Use Cases

#### Scenario 1: Customer Service Quality Monitoring

**Requirement**: Supervisors need to review all conversations containing the keyword "refund" to evaluate handling quality

**Steps**:

1. Enter "refund" in the search box
2. Set the time range to "Last 7 days"
3. Review each search result to verify handling meets standards

#### Scenario 2: Issue Tracking

**Requirement**: A user reports an issue and you need to find related historical conversations

**Steps**:

1. Enter the username or key issue description
2. Review past conversation records
3. Understand the issue history and resolution status

#### Scenario 3: Performance Analysis

**Requirement**: Analyze inquiry volume and issue types for a specific product

**Steps**:

1. Search for the product name keyword
2. Export search results (if supported by the system)
3. Analyze common issues and improvement directions

***

### FAQ

#### Q: Does search speed depend on the number of conversations?

**A**: The system uses high-performance search technology, so results are returned within 1-2 seconds even with a large number of conversations. However, using time range filters is recommended for the best experience.

#### Q: Is search case-sensitive?

**A**: No. The search is case-insensitive and returns the same results regardless of capitalization.

#### Q: Can I search for multiple keywords at once?

**A**: Yes. Enter multiple keywords separated by spaces, and the system will search for conversations containing any of the keywords.

Example: Entering "return refund" will find conversations containing "return" or "refund."

#### Q: Is search history saved?

**A**: The system saves recent search keywords for quick repeat queries. Search history is stored in the browser; clearing browser data will also clear search history.

#### Q: Why can't I find certain conversations?

**A**: Possible reasons:

* The conversation has been deleted or archived
* You don't have access permission for that conversation (restricted by role permissions)
* Keyword spelling error
* The conversation time is outside the filter range

***

### Notes

{% hint style="info" %}
**Permission Details**

Search results are restricted by your role permissions:

* You can only search chat platforms you have access to
* You can only search conversations related to AI Assistants you have access to
* Organization owners can search all conversations
  {% endhint %}

{% hint style="warning" %}
**Performance Tips**

* Avoid using overly common keywords (such as "hello" or "thank you"), as they return too many results
* Use time range filters to narrow search scope
* Regularly archive old conversations to keep the inbox organized
  {% endhint %}

***

### Related Features

{% hint style="info" %}
**Additional Features**

* [All Conversations](/maiagent-user-guide/maiagent-user-guide-en/conversations/reply.md)
* [Conversation Viewer](/maiagent-user-guide/maiagent-user-guide-en/conversations/conversation-viewer.md)
* [Reply Quality Control](https://github.com/Playma-Co-Ltd/maiagent-user-guide-gitbook/blob/main/en/channels/quality.md)
  {% endhint %}


---

# 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.maiagent.ai/maiagent-user-guide/maiagent-user-guide-en/conversations/inbox-search.md?ask=<question>&goal=<endgoal>
```

`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.