{"id":444,"date":"2020-03-10T09:27:37","date_gmt":"2020-03-10T16:27:37","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/microsoft-copilot\/blog\/copilot-studio\/building-a-crisis-faq-bot-using-power-virtual-agents\/"},"modified":"2024-06-05T05:42:44","modified_gmt":"2024-06-05T12:42:44","slug":"building-a-crisis-faq-bot-using-power-virtual-agents","status":"publish","type":"copilot","link":"https:\/\/www.microsoft.com\/en-us\/microsoft-copilot\/blog\/copilot-studio\/building-a-crisis-faq-bot-using-power-virtual-agents\/","title":{"rendered":"Building a Crisis FAQ bot using Power Virtual Agents"},"content":{"rendered":"

There are a wide range of circumstances organizations experience that require communication tools to be created and deployed efficiently. We have heard from several customers who\u2019ve successfully used Power Virtual Agents for this purpose, so we\u2019ve put together this blog post to highlight some best practices and tips for building a crisis response bot (\u201cCrisis FAQ bot\u201d) for your organization.<\/p>\n

A Crisis FAQ bot can help you address some common questions of employees, for example, in the face of crisis. You can sign up for the Power Virtual Agents<\/a> trial version to create a bot (trial is free for 30 days and currently extendable after 30 days) and use the pointers outlined in this blog to create and customize topics as needed for your audience. This blog also walks you through an example with step by step guidance that you can expand for other scenarios. The key goal of this blog is to help you get a Crisis FAQ bot deployed quickly.<\/p>\n

\"Images<\/p>\n

Identify the topics to design<\/strong><\/h3>\n

Taking some time to plan your topic coverage for your Crisis FAQ bot will help you make most efficient use of your authoring time and give your bot the best chance to successfully answer the questions from your users.<\/p>\n

When first thinking about what topics your Crisis FAQ bot will need, it can be helpful to think about all the interaction points customers\/employees\/students have with your organization. It\u2019s essential to consider this from the point of view of the people who will be using the bot.<\/p>\n

Below is an example of some key suggested topic groups for a bot built to handle a crisis response. This example is based on similar crisis efforts like the CDC site FAQ.<\/a><\/p>\n

    \n
  1. Emergency contact information for your organization<\/li>\n
  2. Advisories specific to your organization<\/li>\n
  3. General public health information (for example, based on CDC site FAQ<\/a>)<\/li>\n
  4. Preventive measures and tips (based on CDC site FAQ<\/a>)<\/li>\n
  5. Exposure assessment (based on CDC site FAQ<\/a>)<\/li>\n
  6. Frequently Asked Questions (based on CDC site FAQ<\/a> and on actual questions that have been asked of your organization from all sources, including your bot in production)<\/li>\n<\/ol>\n

    \"\"
    \nThese topics can be <\/span>    created and configured<\/a> in the Power Virtual Agents authoring canvas as shown below. <\/span>
    \n\"Image<\/p>\n

    You can also automatically generate a set of topics from the CDC site FAQ<\/a> or another online content source, using the Suggested topics <\/a>feature in Power Virtual Agents. This will generate a list of topics and trigger phrases using the content from the FAQ website. You can then review and add the applicable topics from this auto-generated list to your bot.<\/p>\n

    \"\"<\/p>\n

    Getting the user to the information they need<\/strong><\/h3>\n

    Write down the questions the user might ask the bot that should start a topic. These are your topic \u201ctriggers.\u201d<\/p>\n

    Then, write down the questions the bot should ask to narrow down the scope of the problem. (Asking as few questions as possible in the bot conversation keeps your user engaged and keeps your bot authoring efforts efficient.) <\/span>What are the possible responses to your questions?<\/p>\n

    Use these questions to create a logical conversation tree for the steps needed to determine which answer your user needs (in other words, so that you know exactly what the issue is).<\/p>\n

    In this content design example, a user saying \u201chi\u201d or asking a vague question (“I need help”) will see the Greeting topic, which redirects to a topic that asks which general topic the user is interested in. Each topic group will ask clarifying questions to branch out to individual topics, and the user will be guided to the answer they are looking for. If the user starts by asking a specific question, it will trigger the specific topic directly, based on the trigger phrase associated with it.<\/span><\/p>\n

    Some guidelines to keep in mind as you build out the trigger phrases and topics:<\/p>\n

      \n
    1. You can think of each topic as having a unique verb, noun, or verb + noun combination (e.g.: travel, meetings, working remotely). If you find that it is hard to differentiate the triggers for two topics, consider combining those two topics and guiding your users with questions within the combined topic.<\/li>\n
    2. Within the trigger phrases for a topic, use a variety of words that your users will likely use to mean the same thing. (eg, “travel” “trip” “visit a customer” “go to an event”)<\/li>\n
    3. For words that are common across multiple topics (such as your company name)\u00a0 there is no value in adding them to trigger phrases because it does not help the AI to differentiate the topics.<\/li>\n<\/ol>\n

      Let\u2019s take an example use case and walk it through.<\/p>\n

      Example topic: travel policy<\/strong><\/h3>\n

      User wants to know company specific information regarding travel policy during crisis.<\/p>\n

      Triggers<\/strong><\/h4>\n