- Use the All Conversations view
- Understanding library conversation cards
- Conversation Summaries
The Conversations view is where you'll find a library of the conversations your chatter's have had with your bot. Simply select a conversation from the list to view the entire transcript. This view also displays your chatter's information, from their email address and device information, to the metavariables and global variables associated with their conversation.
What is a "conversation"?
When it comes to Ada chatbots, a conversation is the interaction between your bot and the chatter.
How are conversations organized?
The left-hand panel of the Conversations view contains the conversations library. This is a scrollable list organized by chatter, with the most recent conversations appearing at the top of the list. You can filter the list by date, or by a number of conditions, such as by a specific Answer, variable, or whether or not the conversation contains a handoff to an agent. You can learn more about the filters in the Search and filter the conversations library.
How often are conversations updated and how long are they stored?
The Conversations view updates roughly every 2 minutes, and conversations are stored on the dashboard for 6 months. Conversations older than six months move to the archive.
Use the All Conversations view
The All Conversations view contains a list of conversation cards organized by chatter. This is the conversation library. Selecting a card in the library displays the transcript of that chatter's interactions with your bot, as well as the information your bot has collected about the chatter.
View chatter conversations
- On the Ada dashboard, go to Conversations > All Conversations.
- In the conversations library in the left-hand panel, click a conversation card to open it.
This displays the transcript of the chatter's conversations with your bot in the center panel, as well as the chatter information in the right-hand panel.
- To hide the chatter information panel, hover over it, then click the three-line menu that appears in the upper right corner. To open it again, click the Details button in the same upper right corner.
Train Answers from the conversation transcript
You can train chatter messages to Answers directly from the conversation transcript.
- In the conversation transcript, select a chatter's message, or highlight a portion of it.
- Click the drop-down menu that appears and select an Answer to train the chatter's message to.
To learn more, read our guide about how to train Answers from the All Conversations view.
Conversations remain available in the conversations library for six months before becoming archived. Archived conversations are no longer accessible from the All Conversations view. Contact your Ada team to have archived conversations released back to your dashboard.
Understanding conversation library cards
The conversations library appears in the left-hand panel of the Conversations view. By default, the conversation cards are sorted by date and time, with the most recent conversation appearing at the top.
Conversation cards, themselves, display some basic preview information about the chatter and interactions it contains. Some of this information may be clear to understand, like the chatter's name, or the date. Other indicators may not be so straight forward at first glance.
The following list breaks down the various elements that make up a conversation card:
- Chatter label – This label appears at the top left of each conversation card, and identifies them based on their associated chatter.
There are four ways the chatter label can identify the chatter:
- Name or email address – If your bot collected a name or email variable for the chatter, the information from one or the other appears as the chatter label, with the chatter's name taking precedence.
- Anonymous – If your bot collected neither the name nor email variable, anonymous appears in place of the chatter's name or email address.
- Test User – This label appears for conversations you or your team create using the Test Bot.
- Engagement status – The dot to the right of the chatter label indicates their engagement status. A green dot indicates they currently have a chat window open and may be engaged with the bot, while a grey dot means their chat window is closed.
- Conversation summary – With enough dialogue to work with, your bot can discern the chatter's statement which best summarizes their intent. When available, this statement appears beneath the chatter ID.
- Satisfaction – An icon of a heart within a speech bubble indicates which chatters were served the Satisfaction block during their conversation. The numerical value to the right of that icon indicates the chatter's satisfaction response.
- Agent avatar – For those clients with an Ada Glass integration, an avatar image indicates which agent the chatter corresponded with during the course of the conversation.
Search and filter the conversations library
A search bar and filter drop-down menus appear at the top of the conversation library. Use these to search your conversations directly, or filter them based on the date, or other available parameters.
Use the search field to search your conversations based on text contained within the chat transcript. This could be anything from the chatter's name or email address, to key words or phrases they might have used during their conversation.
Filter by date
Filter the list based on a date range. Click the calendar drop-down menu, then select a date from the preset date ranges. You can also create a custom date filter.
Filter by condition
In addition to date, there are a number of conditions by which you can filter the conversations library.
- Click the Filter drop-down menu.
- In the configuration dialog box that appears, click the Select filter type drop-down menu, then select a filter type from the list. Use the following table to understand what each filter type means:
Answers Filter your conversation library to show only conversations in which a specific answer was served to your chatters. Chatter ID Filter the library by chatter ID. This is the unique identifier assigned to chatters. The chatter ID appears at the top of the chatter information panel. Engaged Filter the library to only show either engaged or not engaged conversations. Handoff Filter your conversation library to show only conversations in which chatters were handed off via email or to a live agent. Language For clients with multilingual functionality enabled, filter your conversation library to show only conversations in a specific language. Satisfaction Rating Filter your conversation library to show only conversations in which chatters provided a specific satisfaction rating. Variable Filter your conversation library to show only conversations in which specific global (green) or meta (purple) variables have been collected.
- Click the center drop-down menu, which is the validation drop-down menu, then select a validation. The validation choices available are determined by the filter type you chose.
- Complete the Value field by using either the drop-down menu or the text input field. As with validation, the input required for this field varies depending on the filter type.
- Click Apply. The conversations shown in the conversations library reorganize according to the filters you set.
- Click + And to add additional filters to sort the library as specifically as you need.
Conversation Summaries help you understand the theme of a conversation at a glance. With enough chatter questions in a conversation, your bot can determine the chatter's intent. Key phrases or sentences are then presented on the Answer card in the conversation library. These phrases should give you a good idea about what the chatter is trying to achieve, helping you identify conversations of interest quickly and easily.
You’ll also find Conversation Summaries at the end of the individual conversation transcripts. Of course, a chatter can have several conversations with your bot. Each of those may have their own summaries!
- Summaries appear on conversation cards in the Conversations library.
- Summaries also appear at the end of relevant transcripts in the center All Conversations view panel.
- Summaries include up to three chatter messages.
- It’s possible that a chatter’s intent is not detectable. In that case, there won’t be any summary attached to that particular conversation.
- Summaries only consider the chatter’s text messages, and not button clicks or bot messages.
Summaries are currently only available for English conversations.
Have any questions? Contact your Ada team—or email us at firstname.lastname@example.org.