{"id":20909,"date":"2023-04-19T13:00:51","date_gmt":"2023-04-19T12:00:51","guid":{"rendered":"https:\/\/www.intercom.com\/blog\/?p=20909"},"modified":"2025-01-03T13:27:21","modified_gmt":"2025-01-03T13:27:21","slug":"knowledge-base-best-practices","status":"publish","type":"post","link":"https:\/\/www.intercom.com\/blog\/knowledge-base-best-practices\/","title":{"rendered":"Get ready for AI bots by optimizing your knowledge base"},"content":{"rendered":"

A great knowledge base has always been a crucial element of effective, personalized support. <\/span><\/p>\n

Now, with the advent of AI agents like <\/span>Fin<\/span><\/a>, well-structured, comprehensive, up-to-date knowledge bases will be front and center.\u00a0<\/span><\/p>\n

What is a knowledge base?<\/span><\/h2>\n

A knowledge base, or help center, is a collection of <\/span>articles<\/span><\/a> that contain helpful answers, tips, and other important information related to your product or service that customers can easily search from one centralized location.<\/span><\/p>\n

Fin<\/span><\/a>, Intercom\u2019s AI Agent, can consume all the information in your knowledge base, help center, or any public URL within minutes to immediately offer your customers accurate and trustworthy answers.\u00a0<\/span><\/p>\n

If your help content is well-written, well-structured, and covers everything you want an AI bot to be able to answer, you\u2019re essentially ready to go. Nevertheless, there are a couple of things you can do to ensure your content is optimized for AI support, both around creating new help content, and optimizing existing content.<\/span><\/p>\n

Do you have more questions about Fin? Learn more from the topics raised at our recent Q&A session<\/a><\/p>\n

Optimizing your knowledge base for AI support<\/span><\/h2>\n

So how do you make sure your knowledge base is ready to work with an AI agent (or chatbot)?\u00a0<\/span><\/p>\n

1. Create new content to fill gaps in your knowledge base<\/span><\/h2>\n

Now is the time to audit your help center or knowledge base content. Are there gaps you\u2019ve been meaning to fill, but you just haven\u2019t gotten around to it? To experience the full benefit of an AI tool, it\u2019s important that any solution that can be added to your knowledge base, is.\u00a0<\/span><\/p>\n

Our own Support team ran a full audit of more than 700 articles before adding Fin, to ensure all information it accessed would be accurate and up-to-date \u2013 and that any gaps were filled.<\/span><\/p>\n

When you know something inside and out, identifying what others may find confusing can be a challenge. Ask yourself these questions:<\/span><\/p>\n

    \n
  • Are there trends or patterns among your customer conversations that a help article might address?<\/span><\/li>\n
  • Look at your saved replies; are there any that might make sense as a help center article? Even if the content doesn’t seem substantial enough for its own article, it’s a good idea to add an FAQ article for short snippets of information that have no other obvious home.<\/span><\/li>\n
  • What questions are making their way through to your support team? Are there incidences where your customers should have been able to self-serve, but the material was unavailable?\u00a0<\/span><\/li>\n
  • If help articles already exist, do they need to be optimized to prevent customers bypassing them in favor of your team?<\/span><\/li>\n<\/ul>\n

    Tips for rapidly producing valuable new help content<\/h3>\n

    Create templates for common topics<\/strong><\/h4>\n

    Your support team members shouldn\u2019t have to build every new article from scratch. Building a template for your knowledge base documentation \u2013 even if it\u2019s just a simple sketch or document \u2013 will help your team understand what a successful article should look like, and make production much quicker. A sample template might look something like this:<\/span><\/p>\n

    \"\"<\/p>\n

    Collaborate with other customer-facing teams<\/strong><\/h4>\n

    It\u2019s important to seek regular feedback from other customer-facing teams to gain critical insights that drive growth and improve your product or service.\u00a0<\/span><\/p>\n

      \n
    • Reach out to your sales team, and any other team that frequently interacts with your customers, to find out the issues they\u2019re encountering in their interactions. These feedback loops provide additional context on your customers\u2019 issues so you can tailor your solutions to their preferences and needs.<\/span><\/li>\n
    • Build a culture of knowledge management across these teams, encouraging them to use the knowledge base as their own support tool, and to flag content that needs updates, improvements, or elaboration.<\/span><\/li>\n<\/ul>\n

      2. Optimize and update existing content<\/span><\/h2>\n

      The more simple, straightforward, and comprehensive your articles are, the easier it will be for AI bots like Fin (and your customers) to consume them. If it\u2019s confusing for a human to read, it\u2019ll be confusing for Fin aswell. Focus on:<\/span><\/p>\n

        \n
      • Simplifying language:<\/b> Think about how your users frame questions and ensure that the answer is phrased in a relevant and accessible way. Avoid basic \u201cyes\u201d or \u201cno\u201d answers; instead, use full sentences to disambiguate the answer for Fin, and ultimately, for your customers. For example, your customer asks \u201cDo I need to use the original outer shipping box to return an item?\u201d. Instead of saying \u201cno\u201d, say something like \u201cYou can use your own packaging when sending an item back for a return or exchange, no need to save the original shipping<\/span> box<\/span>.<\/span><\/i>\u201d<\/span><\/li>\n<\/ul>\n