Top 10 Chatbot FAQs

Chatbots have quickly moved from lofty vision to technological reality. In fact, 61% of consumers think that chatbots are the future of customer service. However, as chatbot technology has advanced and become more nuanced, gaps still remain between the promise of value and its actual delivery.

These gaps aren’t caused by bot technology itself, but rather by misplaced expectations of performance or a lack of thorough understanding of the various types of bots available.

AI and Bots: Are you ready?

AI and Bots: Are you ready?

Register for our webinar to discover the most promising bot and AI technologies available today and how each can contribute to better customer care and agent productivity.

Reserve my seat
Webinar

To help bridge these gaps, we’ve compiled the top 10 chatbot frequently asked questions (FAQs) to get you started on your journey.

    1. What are some bot-specific terms I should know?
    2. What can I expect from a bot?
    3. How do I know if bots are right for me?
    4. What can my agents do with the bots?
    5. How do bots improve the customer experience?
    6. What percentage of chat volume can bots handle?
    7. What are some key bot features?
    8. What are some of the challenges can I expect with bots?
    9. What accessibility or security concerns are there with bots?
    10. How do I know if my bots will be successful?

Q1: What are some of the bot-specific terms I should know?

When you’re first diving into the world chatbots, you may hear people talking about different terms like ‘Natural Language Processing’, ‘Machine Learning’, and ‘Intents’, but have no idea what they mean. Here are the definitions to the top seven bot-specific terms you need to know:

  1. Intents: An intent is the intention of a visitor. Intents represent the visitor’s purpose or goal, like booking a flight, paying a bill, or finding a news article. Intents are contained in the questions that visitors ask chatbots.
  2. Entities: Pieces of information which provide more context to an intent. They might be times, dates, places, people, or other pieces of information which adjust the intent to a visitor’s specific needs.
  3. Natural Language Processing (NLP): A form of artificial intelligence that enables chatbots to understand conversational dialog and identify intent.
  4. Machine Learning: Algorithms that help a chatbot to “learn” concepts using data — without being explicitly programmed. For example, chatbots gain more confidence in their responses based on feedback from agents and customers.
  5. Sentiment Analysis: An automated process that allows a chatbot to extract verbal cues from chats to determine the mood and feelings of a visitor and adapt responses accordingly.
  6. Decision Tree: An “If this… then that” framework that guides the customer to choose from a list of pre-defined scripts and options. This framework can be presented either through keywords or buttons.
  7. Bot Sensitivity: When a visitor asks a bot a question, it will calculate a Matching Score in real-time for every intent in its library. The higher the Matching score, the more confident the bot is that an intent should be used as an answer for that particular question. It will then use the intent with the highest Matching score as the answer, provided it meets the sensitivity parameters.

Q2: What can I expect from a bot?

Different types of bots can handle different use cases. Here are some examples:

  1. FAQs: Chatbots can handle questions like ‘What are your store hours?’, ‘Which location is closest to me?’, and more, freeing up your agents to handle the more complex queries.
  2. Gathering customer information: Bots can pass off the who, what, where, when, and why to an agent, helping them contextualize queries and reducing time spent on each chat.
  3. Triage queries: Thanks to bot’s smart routing capabilities, customer queries can be routed to the appropriate department or agent.
  4. Shorter queues, faster responses: Chatbots can handle a virtually unlimited amount of chats simultaneously, cutting down on response time for customers. They can also deliver responses more quickly than human agents.
  5. 24/7 service: Bots provide an additional channel for customers to still get answers during off hours when a human agent is not available.

If you have customers, bots are right for you. A common misconception is that bots are only useful if you meet certain criteria or have certain scenarios. In reality, all businesses can benefit from bots, no matter the size.

The better question is: Which type of bot is best for you? Chatbots come in many sizes and shapes. Even if you don’t have a particularly high chat volume, your agents can still benefit from an agent-facing bot. Another example is even if you don’t have live chat, your customers can benefit from social media bots.

Q4: What can my agents do with bots?

Bots aren’t just customer-facing — they can also help your agents be more efficient and productive. Agent-facing bots live directly in the agent console and analyze previous and current chat interactions to suggest responses, links, videos, and other resources that may be suitable. These functionalities mean that your agents can use bots to deliver accurate responses to customer queries more quickly.

Q5: How do bots improve the customer experience?

Bots improve the customer experience by giving your customers the quick answers they demand, on their terms, anytime and anywhere they want. With the ability to provide 24/7 customer service and take on a virtually unlimited amount of customer queries simultaneously, bots are your queue busters and central automated hubs of information.

Taking it a step further, if your bot can’t answer a query, it’ll automatically route the customer to an agent who can – while also handing off the transcript to help the agent contextualize the interaction. No channel pivoting means no customers falling through the cracks. That’s a customer experience win.

Q6: What percentage of chat volume can the bot handle?

According to our benchmark report, bots are currently involved in 59% of all chat interactions1 in 4 of those are handled from start to finish without an agent. Your chatbot volume distribution will naturally vary between business hours and off-hours.

During business hours, bots should be your first line of defence for FAQs. Then there are customers that you would want instantly routed to an agent, like VIPs, those with urgent technical issues, or other specific criteria that apply to your business. Taking those parameters into consideration, bots should be handling at least half of all incoming chat volume.

During off-hours, your bots should be the first touch for 100% of all queries, with the ability to pass the more complex offline messages to an agent at a later time.

Q7: What are some key bot features?

As mentioned previously, different types of bots will have varying features. That said, there are some key features that are non-negotiable:

  1. Handing conversations off to an agent: Eighty-six percent of consumers believe they should always have the option to transfer to a live agent when dealing with a chatbot. When looking for features, this one is your first priority.
  2. Smart routing: This feature ties into the one above. Not only should the bot be able to hand off conversations, but they should also be able to route the customer to the right person in the right department.
  3. Integrations: Whether it’s a webhook to grab location information, or a CRM integration to access a customer profile, a chatbot is only useful when it’s integrated into your current technology stack.
  4. Small talk: Just because it’s a ‘bot’ doesn’t mean it has to be robotic. Customers enjoy having a little fun with a chatbot and your bot should be able to play ball.

Q8: What are some of the challenges can I expect with bots?

The hardest part is getting started. Once you kick off the process and have your ducks in a row, everything else is smooth sailing. You can expect to face challenges while building your bot if you don’t plan it out properly.

For example, if you build a bot without first analyzing your chat transcripts, support emails, and phone calls, it might not be helpful to your customers. Other examples like not assigning clear ownership of the bot, not testing it prior to rollout, and/or maintaining it will cause challenges if not planned properly.

You need to align your bot with both business goals and customer needs and create a comprehensive deployment strategy otherwise you’ll have problems down the line.

Q9: What security concerns are there with bots? 

Chatbot technology has no specific security concerns that differ from any other system. While you may have industry-specific requirements (like HIPAA or FEDRamp compliance), the technology itself is no less ‘safe’ or ‘secure’ than any other platform. As long as your website and technology stack itself are set up securely and you take steps to ensure that your customer data is secure, then there’s no need to worry about security breaches with a bot.

That said, not every bot platform adheres to the same standards (just like other software). If you have specific requirements, get your IT team involved and ask the tough questions before you choose a bot vendor.

Q10: How do I know if my bot will be successful?

As with any technology investment, chatbots are only as good as how they’re implemented and maintained. But if you plan and build out your bot with clear objectives and measurable milestones, success will be within your reach. You will know if your chatbot is successful through agent and customer feedback; decreased offline messages; and/or improved KPIs such as CSAT, shopping cart conversion, and others specific to your use case.

Wrap-up

While bots may seem daunting at first, just remember one simple thing: Chatbots are automation systems designed to make your business run more efficiently. If you can clearly articulate your goals and stay focused on them, you will succeed. You don’t need to be a bot expert or know how to code complex scripts to build a successful chatbot. Answering these essential questions will get you 80% of the way there – the remaining 20% is tailoring the bot to your specific requirements.

AI and Bots: Are you ready?

AI and Bots: Are you ready?

Register for our webinar to discover the most promising bot and AI technologies available today and how each can contribute to better customer care and agent productivity.

Reserve my seat
Webinar

About Jeff Epstein

Jeff is Comm100’s VP Product Marketing and Communications. He’s a B2B marketer with 20+ years’ experience creating compelling messaging and content for sales enablement and demand generation. Having held roles with companies including IBM, General Motors, and Comm100, Jeff knows how to connect solutions to buyers.