Imagine this: You’re a candidate on the hunt for a new job. You visit a company’s career site, where you’re greeted by a friendly chatbot at the bottom of the screen. But when you ask it a question, you’re disappointed by the following response: “Our reps typically respond within a few hours. Want to give us your email address?” Or worse—“Sorry. I’m not that kind of chatbot.”
Frustrating, right? Unfortunately, that experience is all too common as companies eagerly adopt chatbots to improve the candidate experience on their websites.
The best recruiting chatbots are able to seamlessly handle many types of interactions, like searching for jobs, screening candidates, scheduling interviews, and answering frequently asked questions (FAQs). They also do it in a way that is natural, as if the candidate were having a conversation with a real recruiter.
But how does a chatbot know what information to provide when a candidate asks a question? And what about answering common questions about the company?
That’s where a knowledge base comes in. A knowledge base provides your chatbot with the information it needs to accurately respond to user questions. Chatbots powered by AI are designed to recognize the general intent of what a candidate is asking. But without a knowledge base, it won’t know how to respond in a useful manner—chatbots need you to teach them what to say and how to say it.
What is a Chatbot Knowledge Base?
Think of a knowledge base as the brains behind your chatbot. It is a collection, or repository, of information about your company that is maintained by you and deployed by your chatbot at just the right time: when it’s requested.
Your knowledge base allows you to structure content around FAQ topics aimed at providing company-specific details, and accounts for the variety of ways people ask for the same information.
Check out our video, What is a chatbot knowledge base?
Why are FAQs important?
Great (frequently asked) question! FAQs are typically used on a corporate site or career site to proactively provide helpful information. For talent acquisition teams, they’re often used to establish consistent communication and help with education around the application, interview, and hiring process.
FAQ sections on career sites are designed to consolidate this information to make it easy for candidates to find. But there is a better way to deliver this information that’s more engaging and meaningful to the user: through a chatbot. And that’s where your knowledge base comes in.
Let’s take a look at the key knowledge base elements you should be aware of when planning how to deploy and maintain your chatbot.
1. FAQ Topic: What questions should my chatbot be answering?
To prepare your chatbot to interact with candidates, you need to add questions you anticipate them asking. There is no single list of topics that can account for everything candidates want to know about your company. You’ll need to identify the most common questions asked by candidates. It can sound overwhelming at first, but start small. Focus on 10 questions to begin with, and grow from there.
Need FAQ ideas?
Check out our template, 170+ Screening Questions & FAQs Your Chatbot Should Know!
2. FAQ Response: How do I want to answer this question?
Each FAQ you add will require a response, which the chatbot delivers to the candidate when they ask a related question. Responses could be a pure text reply or a link to additional information that’s too lengthy to include within the chatbot window. You could also include a video, which would be great for questions around company culture or showcasing employee testimonials.
3. FAQ Related Phrases: How do I account for candidates asking the same question in multiple ways?
Since there are multiple ways to ask the same question, related phrases will serve as the training data for your FAQ topics. These don’t have to be questions necessarily. They can be short phrases or even individual keywords. The important part is giving your chatbot enough context to understand when it should be offering that response. For a topic such as “Lunch options,” related phrases could include “Where can I get lunch around the office?”, “Recommend a good lunch spot near the office,” and “Lunch options nearby.”
4. FAQ Tags: How should I sort my FAQs?
Easily sort your FAQ topics with tags to make it easier for you to maintain your knowledge base. One way you can use tags is to group topics by job category or location. You might provide different benefits in one job category compared to another, or maybe public transportation options to get to the office are different from one location to another—either way, you’ll want to ensure job seekers are receiving the most accurate, relevant information.
5. Unanswered Questions: What are we missing?
This is a very important piece of your knowledge base. One major benefit of having the chatbot connected to a knowledge base is its ability to store and surface topics that you missed at deployment. When a candidate asks a question that the chatbot is unable to answer, that question is flagged as unanswered. As you review your knowledge base, you’ll be able to add them as new questions your chatbot can answer.
6. Fallback Responses: What about questions that should be answered by a recruiter?
The creative potential of the human race knows no bounds. The downside to that is there will always be some topics your knowledge base is unable to address. And that’s OK. Sometimes you need to direct a candidate to a human expert who can address the question(s) in more detail. Your fallback responses can help you do that by quickly providing the candidate an outlet to get in touch with a person. Craft a message such as, “If you need to contact us with a detailed request, email us at HR@yourcompany.com” or include a phone number to get in touch.
Training Your Chatbot for Ongoing Success
To better serve your candidates, a knowledge base will help you maintain important information in easily digestible bits that are perfect for a chatbot.
Ready to learn more about launching, maintaining, and training your chatbot? Watch our on-demand webinar.