Leverage Your Existing KCS Knowledge Base to Launch Chatbot
Technology | September 16, 2019
A traditional knowledge base consists of one or more long-form templates, each with its own content and meta fields. A typical problem-solution article has the following fields,
- Meta: Product, Feature, Version…etc.
A problem-solution article could be as small as 100 words and be as long as a few thousand words with screenshots, tables, and videos. The success of these articles depends on two key factors,
- The power of Google to index each and every word of the article and suggest a list of articles relevant to customer keywords. Google also considers metrics like CTR, keyword density, site ranking…etc to rank results.
- Customer readiness to adapt to the technical depth, level of detail, and style in order to find the information they want.
With chatbot it all changes,
- There no Google , your bots NLP and search engine does the heavy lifting.
- Chatbot gets just one chance to get it right , unlike Google search page which can provide several results ranked by relevance.
- Customers are willing to share more ; The avg length of a search query in Google is less than 2 words however the length of issue description in a chatbot is more than 3 words.
- Customers expect a crisp and direct resolution, preferably without navigating out of bot window.
It is common to find Chatbot solution vendors maintaining their own content repository for consistency and indexing advantages. If you don’t have a support knowledge base already or your core support strategy revolves around chat and virtual agent, it is recommended to start your chatbot content program on the vendor solution. However, if you have a mature KM and self-service program that is already serving customers and internal audiences, why not take full advantage of it and be ahead in the game.
Considering most enterprises already have a KM program, let’s look at specific components and best practices to add to your existing content structure and make it bot ready.
- Phrases : These are variations of the title or issue description. Customers describe a question or issue in multiple ways and it is critical we capture the most common once related to the question or problem. UI and backend should support authoring phrases. This will be searched by chatbot solution to deliver the appropriate solution.
- Synonyms : While this has become a legacy concept in Google, it is very important to maintain a list of synonyms in your chatbot search engine. Good news is, most chatbot solutions I looked in to have this feature out of the box. You can also consider integrating your taxonomy, in case you maintain synonyms there.
- Add Chat resolution field to the article template; this is used to author a crisp chat specific response. Below are some best practices to consider when authoring chat responses,
- Keep the answer to less than 100 words. Use bullets or break lengthy solutions into multiple short messages. This will improve readability.
- Wherever possible, provide a link to the detailed process instead of the actual process.
- Use GIFs in place of multiple screenshots.
- Embed videos to illustrate complex processes/troubleshooting steps.
- To begin with, you can also consider auto-filling this field by combining Title – Summary – Link of the article. Later revisit the top used article to write custom chat solution.Tip: Use 80:20 to identify top content and have chat solution written only for them during launch.
- Here is an example in which I have used the above best practices to compose a chat response for this article
When you look for chatbot solution, ensure most of this is covered and if they offer out of the box integration with your current KM solution that will be a huge plus.
This setup fits seamlessly into existing practices like Knowledge Centered Services (KCS®) *. Hope these insights help you in your chatbot journey and boost your customer experience.