Using Microsoft Power Virtual Agents  Boost conversations feature

Boosted conversations, Microsoft Power Virtual Agents -

Using Microsoft Power Virtual Agents Boost conversations feature

Try increasing your topic coverage with real-time responses using information from your website

When designing and creating a chatbot, you'll likely encounter situations where your bot users ask questions that your bot doesn't have an answer

However, by utilizing the boosted conversations in Power Virtual Agents, your bot can find and present information from an external source - even if you haven't created a topic for it.

In the past, when a bot couldn't determine a user's intent, it asked the user to rephrase their question.

If, after two prompts, the bot still couldn't determine the user's intent, the bot escalated to a live agent by using the system Escalate topic.


Before involving a live agent, the bot uses natural language processing to:

  • Parse what a user types to determine what they're asking

  • Find, collate, and parse relevant information from a specified URL (for example, your company's website) with Bing Search

  • Create a plain language response and then deliver that to the bot user

This means you can quickly create and deploy a functional bot, without having to first manually author multiple topics that may or may not cover all the questions your customers might end up asking.

Your workflow might be like this:

  1. You create a bot and enable this capability. You test it thoroughly.

  2. After testing it, you publish your bot so you can instantly provide answers, help, and guidance to your customers or bot users.

  3. You create individual topics for the most important or most often-asked questions from your customers (which you might have developed based on analytics from previous bots or existing support issues).

This could take a while and some specialized knowledge -

But with Boost conversations enabled you're up and running from day one. :)

See more details here


0 comments

Leave a comment

Tags
#WebChat .container iframe{ width: 100%; height: 100vh; }