Watch the video
What's Conversation Assist?
Conversation Assist offers recommended bots and answers to your agents inline in their conversations with consumers, and on-demand within a dedicated widget.
When your agents take advantage of these just-in-time recommendations, they become more efficient and save time. What's more, their conversational outcomes are improved and more consistent. Conversation Assist can even help to reduce the time to onboard new agents.
You can set up bot and answer recommendations in just a few clicks.
On the Home page of Conversation Assist, you'll find a dashboard of rich analytics, which you can use to continuously monitor and tune recommendation performance. Use this valuable data to understanding the impact that your solution is having on your agent operations.
Just getting started? Complete the Using Conversation Assist tutorial.
Inline versus on-demand recommendations
Conversation Assist offers two types of recommendations:
- Inline recommendations
- On-demand recommendations
Inline recommendations
Inline recommendations are answers and bots offered in real time directly within the conversation with consumer. They're based on the intent that's detected in the consumer's message.
On-demand recommendations
Sometimes your agents need more flexibility within conversations. Sometimes, they need to be able to look up answers and bots on demand, regardless of what the consumer just said. The On-Demand Recommendations widget meets this need.
Use either type or both types
You can choose to offer your agents inline recommendations, make available the On-Demand Recommendations widget, or do both.
When offered a recommended answer, the agent can send it to the consumer. The agent can optionally modify it before sending it.
When offered a recommended bot, the agent can delegate the conversation to the bot, so it takes over. The agent stays in the conversation, so they can monitor the bot’s progress and remove the bot if needed.
Rich or plain answer recommendations
Currently, rich answer recommendations are supported only on the Web and Mobile SDK channels.
When offering your agents answer recommendations, you want them to be relevant. But you also want them to be engaging, right? We agree.
So, when it comes to offering answer recommendations, you have options: You can offer plain text answers. Or, you can offer both rich and plain answers, and let your agents choose which type to send within the conversation. Here below, we’ve done the latter.
Recommended answer offered in-line in the conversation
Recommended answer offered on demand
Considering supporting rich answers. Their multimedia nature makes them much more engaging than plain answers, leading to a best-in-class experience for the consumer. Learn more.
Answer recommendations enriched via Generative AI
If you’re using Conversation Assist to offer answer recommendations to your agents, you can offer ones that are enriched by KnowledgeAI's LLM-powered answer enrichment service. The resulting answers, formulated via Generative AI, are accurate, contextually aware, and natural-sounding.
More key concepts
Recommendations are intent-based
Conversation Assist offers recommendations based on the intent that’s detected. For an inline recommendation, this is the intent detected in the consumer’s message. For an on-demand recommendation, this is the intent detected in the agent's query.
Recommendations are skill-based
Recommendations aren’t just intent-based, they’re skill-based too.
When Conversation Assist offers a recommendation, it always does so based on not just the detected intent, but also the conversation’s assigned skill. This means you can "map" a slice of content to desired skills.
You also have the option to further limit recommendations to agent groups and/or profiles.
When inline recommendations are offered to an agent in a conversation assigned to skill A, if the conversation is subsequently transferred to skill B, those recommendations remain available to any agent that picks up that conversation on skill B. This is the case even though recommendations shouldn’t be offered to conversations assigned to skill B, i.e., no configuration rule for skill B exists in Conversation Assist. The recommendations remain available for 24 hours, as the cache of recommendations stored in memory is cleared automatically every 24 hours. We’re actively working on a fix for this issue, so stay tuned!
Multiple recommendations
You can specify the maximum number of recommendations offered by Conversation Assist at a given time. You can offer up to five.
Learn more about how recommendations are offered.
Recommendation sources
Recommendation sources include knowledge bases and bots.
Access Conversation Assist
- Log into Conversational Cloud.
-
Open the menu on the left side of the page, and select Automate > Conversation Assist.
Try the tutorial
If you're just beginning with Conversation Assist, we recommend the Using Conversation Assist tutorial.