# Manage Chat History
# Overview
AI desk Pro's 'Manage Chat History' feature provides a comprehensive overview of past interactions, helping administrators and users to track, revisit, and reflect upon their conversations. This interface lists the exchanges, systematically organized with titles, users, channels, and timestamps for easy navigation. The history ensures transparency and continuity, which can be vital for understanding user behavior, auditing interactions, and maintaining a record of the AI's performance over time.
# Actionable Options for Chat History
In the 'Manage Chat History' section, users are empowered with direct actions to manage their data efficiently:
- Details: View the interaction in a chat, providing context to the conversation and the ability to review the AI's responses in detail.
- Delete: Remove a chat history entry when it's no longer needed, ensuring the user's data remains relevant and organized.
- Evaluate: Upon clicking a chat in detail, there will be 'Evaluate' button available. Assign a rating and leave comments for each specific interaction, contributing to the AI's learning process and service improvement.
# Evaluating Chat History
Evaluating chat history is an integral part of maintaining the quality of user interactions with AI desk Pro. Each entry in the chat history can be individually reviewed and assessed, allowing for detailed feedback on the AI's responses. Users can rate the quality of interactions and provide comments, which are crucial for continuous improvement of the system. The overall rating of the chat evaluated will be shown in the dashboard, allowing administrators to consult the chat and response quality of AI desk Pro.
This feedback loop not only enhances the AI's learning but also ensures that user experiences remain at the forefront of the service's evolution. Through meticulous monitoring and evaluation, administrators can derive actionable insights and foster an environment of constant enhancement in AI communication strategies.
# Search and Filter the History
The chat history feature in AI desk Pro allows users to easily find past interactions using an intuitive interface. At the top of the history panel, you'll find:
- A keyword search bar: Type any keyword or phrase to quickly retrieve relevant conversations.
- A user search box: Type a user's name to show only that person's conversations. The match ignores case and accents.
- A channel filter: Narrow the list to the channel a conversation came from. Choose All channels, Teams, Webchat, MCP, or Notebook. Each session also displays its channel in the list.
- A date picker: Filter your search results by selecting a specific date range.
All filters combine, so you can, for example, review only the Webchat conversations of a specific user during last week.
Benefits:
- Precision: Find the exact interaction you're looking for, even in long conversation logs.
- Speed: Save time by jumping directly to relevant exchanges.
- Monitoring: Improve feedback and quality control with targeted conversation reviews.
This functionality makes it easier than ever to analyze usage patterns, identify potential issues, and improve the user experience with your AI desk Pro assistant.
# How Messages Are Displayed
When you open a conversation's details, each message is rendered according to its type instead of being shown as raw markdown:
- Plain text answers are displayed as formatted text.
- Adaptive Cards (for example, QnA answers or interactive responses) are rendered as the actual card the user saw.
- Dialog references (guided dialogs opened during the conversation) are shown as a dialog entry rather than raw content.
Internal reference tokens that the agent uses to track its sources are stripped from the displayed text, so the conversation reads the way the end user experienced it.
# Citation References
Below an answer that used your knowledge base, the Chat History shows the references the agent actually cited in that answer. Older behavior displayed the full pool of candidate documents retrieved during the search; the view now lists only the sources referenced in the response, matching what the end user saw in Teams or Webchat.
Each reference card shows:
- A badge indicating the source type: QnA, Document, or History (the agent's own conversation history).
- The source title and a snippet of the cited content.
- The Indexation date: the date the content was captured at indexing time. For SharePoint files this is the file's last-modified date, for local documents the upload date, and for QnA entries the last edit date.
- An Open link to jump to the source, where one is available.