> 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/conversation-viewer.md). # Conversation Viewer ### Overview The Conversation Viewer is a conversation review page in the MaiAgent admin interface that allows managers and support agents to view complete conversation records in a clearer, more detailed way. Through the Conversation Viewer page, you can focus on examining all details of a single conversation, including message content, timeline, tool usage records, and more. {% hint style="info" %} The Conversation Viewer is especially useful for quality monitoring, customer service training, and issue tracking, enabling more effective conversation analysis. {% endhint %} *** ### Opening the Conversation Viewer #### From the Inbox 1. **Go to the conversation list** * Click "Customer Service" in the left menu * Click "All Conversations" 2. **Select a conversation to view** * Find the target conversation in the conversation list * Click the conversation to enter the Conversation Viewer page *** ### Interface Guide #### Main Sections
Section NameDescription
Conversation Info PanelDisplays basic conversation information
- Username
- Chat platform (LINE / Facebook / Web Chat)
- Start time
- Conversation status
Message TimelineDisplays the complete conversation record in chronological order
- User messages
- AI replies
- System messages
- Timestamps
Conversation DetailsDisplays advanced information
- AI Assistant used
- Tool call records
- Knowledge base query results
- Token usage
Action ButtonsQuick actions
- Export conversation record (PDF)
- Copy conversation content
#### Message Display * **User messages**: Displayed on the left with a light background * **AI replies**: Displayed on the right with brand-colored background * **System messages**: Centered with gray text * **Timestamps**: Displayed below each message showing the sent time *** ### Advanced Features #### Tool Usage Records The Conversation Viewer clearly displays the tools used by the AI Assistant during the conversation: ``` [Tool Call] Knowledge Base Query Search keyword: Return process Query results: 3 related documents found Time used: 2025-12-10 14:23:15 ``` #### Knowledge Base Citation Tracking If an AI reply references knowledge base content, the citation source is indicated: ``` [Citation Source] Return-and-Exchange-Policy.pdf Related passage: "Returns can be requested within 7 days of receiving the product..." Similarity: 95% ``` #### Token Usage Statistics Displays the token consumption for the conversation: * **User input**: 120 Tokens * **AI reply**: 350 Tokens * **Tool calls**: 80 Tokens * **Total**: 550 Tokens {% hint style="info" %} Token statistics help analyze conversation costs and optimize AI Assistant settings. {% endhint %} *** ### Use Cases #### Scenario 1: Quality Monitoring **Requirement**: Supervisors randomly review conversation quality daily to ensure AI replies meet standards **Workflow**: 1. Randomly select 10 conversations daily from the inbox 2. Review each one using the Conversation Viewer 3. Key checkpoints: * Is the AI reply accurate? * Is the tone appropriate? * Are tools used correctly? * Are knowledge base citations relevant? 4. Flag conversations that need improvement 5. Provide feedback to the AI training team #### Scenario 2: Customer Service Training **Requirement**: Use actual conversation cases to train new customer service agents **Workflow**: 1. Filter out excellent conversation examples (well-handled complex issues) 2. Walk through them step by step using the Conversation Viewer 3. Key focus areas: * How to understand customer needs * How to effectively use tools * How to guide the conversation flow * How to properly close conversations 4. Have new agents simulate similar scenarios #### Scenario 3: Issue Diagnosis **Requirement**: A user reports an incorrect AI reply and the root cause needs to be identified **Workflow**: 1. Find the conversation using the search function 2. Examine it in detail using the Conversation Viewer 3. Analyze potential issues: * Was the user's question correctly understood? * Which tools did the AI call? * Were knowledge base query results relevant? * Review the AI's reasoning process 4. Identify the root cause (insufficient knowledge base / incorrect tool settings / prompt needs optimization) 5. Make the necessary adjustments *** ### Export Conversation Records #### Export Steps 1. Click the "Export" button in the Conversation Viewer 2. The system will export the conversation record in PDF format 3. The PDF file will automatically download to your device {% hint style="warning" %} **Privacy Notice** Exported conversation records may contain user personal information. Please store them securely and comply with privacy policies and applicable regulations. {% endhint %} *** ### FAQ #### Q: How is the Conversation Viewer different from the regular chat window? **A**: The Conversation Viewer provides more comprehensive information, including tool usage records, knowledge base citation tracking, token usage statistics, and other advanced details. It is suitable for analysis, monitoring, and training. The regular chat window is better suited for day-to-day reply operations. #### Q: Can I reply directly in the Conversation Viewer? **A**: No. The Conversation Viewer is a read-only interface designed for viewing and analysis. To reply to a conversation, return to the conversation list. #### Q: Does the Conversation Viewer show deleted messages? **A**: No. The Conversation Viewer only shows existing message records. Deleted messages cannot be recovered or displayed. #### Q: What if the Conversation Viewer loads slowly? **A**: Possible causes and solutions: * **Long conversation**: Conversations with over 100 messages load more slowly — please wait * **Network issues**: Check your network connection * **Large attachments**: Too many images or files can affect loading speed *** ### Related Features {% hint style="info" %} **Additional Features** * [Inbox Search](/maiagent-user-guide/maiagent-user-guide-en/conversations/inbox-search.md) * [All Conversations](/maiagent-user-guide/maiagent-user-guide-en/conversations/reply.md) * [Reply Quality Control](https://github.com/Playma-Co-Ltd/maiagent-user-guide-gitbook/blob/main/en/channels/quality.md) * [Usage Analytics](/maiagent-user-guide/maiagent-user-guide-en/org/usage.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/conversation-viewer.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.