Rules vs AI vs Generative Chatbots
Key Points
- Rules‑based chatbots follow rigid, keyword‑driven flows that often fail when customers deviate from pre‑programmed scripts, leading to misunderstandings and lost sales.
- AI‑powered chatbots with natural language understanding can interpret varied phrasing, personalize interactions, and seamlessly integrate offers and customer data for smoother transactions.
- When a customer’s issue escalates—such as a complaint about a cold pizza—the AI chatbot can recognize dissatisfaction and promptly transfer the conversation to a live agent, preserving the relationship.
- The optimal chatbot type for a business depends on the complexity of tasks, required personalization, and the need for real‑time human handoff, making the choice “it depends.”
Sections
- Untitled Section
- Generative AI Elevates Customer Experience - The transcript demonstrates a generative‑AI‑powered chatbot personalizing a greeting, recommending complementary items, verifying allergen safety, and showing source‑backed answers, illustrating how AI can make interactions more fluent, empathetic, and trustworthy.
Full Transcript
# Rules vs AI vs Generative Chatbots **Source:** [https://www.youtube.com/watch?v=93l-2Usc08U](https://www.youtube.com/watch?v=93l-2Usc08U) **Duration:** 00:05:16 ## Summary - Rules‑based chatbots follow rigid, keyword‑driven flows that often fail when customers deviate from pre‑programmed scripts, leading to misunderstandings and lost sales. - AI‑powered chatbots with natural language understanding can interpret varied phrasing, personalize interactions, and seamlessly integrate offers and customer data for smoother transactions. - When a customer’s issue escalates—such as a complaint about a cold pizza—the AI chatbot can recognize dissatisfaction and promptly transfer the conversation to a live agent, preserving the relationship. - The optimal chatbot type for a business depends on the complexity of tasks, required personalization, and the need for real‑time human handoff, making the choice “it depends.” ## Sections - [00:00:00](https://www.youtube.com/watch?v=93l-2Usc08U&t=0s) **Untitled Section** - - [00:03:21](https://www.youtube.com/watch?v=93l-2Usc08U&t=201s) **Generative AI Elevates Customer Experience** - The transcript demonstrates a generative‑AI‑powered chatbot personalizing a greeting, recommending complementary items, verifying allergen safety, and showing source‑backed answers, illustrating how AI can make interactions more fluent, empathetic, and trustworthy. ## Full Transcript
Have you ever interacted with a chatbot that can't seem to figure out what you need and responds with
"I'm sorry I don't understand. Please try again." Yeah, we've all been there with a rules-based
chatbot, when a simple task of ordering something turns into a headache. Are rules-based chatbots
obsolete? No! But let's look at three different kinds of chatbots with various degrees of
sophistication: the rules-based, AI-powered, and generative AI. Which is the right kind for your
company? The answer is "it depends". Let's look at our first example,
the limited rules-based chatbot, which walks the customer through a rigid, predetermined
flow and operates on basic keyword detection. [chatbot] Thanks for choosing Taste of Italy.
Our pizzas are yummy! How many pizzas would you like to order?
[Bella] Two. [chatbot] What size would you like
them to be? Small, medium, or large. [Bella] Large.
As you can see, there's not much AI involved in this interaction. Of course,
placing an order is not always so straightforward. Because it's impossible for the conversation
designer to predict and pre-program the chatbot for all the ways a person can place an order,
this kind of chatbots often get stuck. [Bella] My pizza is cold! I want to file a
complaint and get my money back! [chatbot] Sorry, I don't understand,
try rephrasing your message. Also, if the customer has a
complaint about the order, the chatbot could act as a gatekeeper. This is a sure
way to send customers to competition. Let's start the conversation again,
this time with an AI-powered chatbot! [Bella] I want to order two large
pepperoni and cheese pizzas. [chatbot] Great choice,
Bella! Would you like any extra toppings? [Bella] No, just the regular, thanks! Add
one apple juice and one beer to the order. With AI and natural language understanding [NLU]
capabilities, the chatbot can understand the customer's request, the first time—no matter
how it's phrased. With deep learning, the longer an AI chatbot has been in operation, the better
it can understand the intention behind questions and provide more detailed, accurate responses.
Let's continue: [chatbot] We have a new offer – order
1 pizza and 1 dessert, and get a drink for free. Would you like to take advantage of this?
[Bella] Of course, who doesn't like dessert? [chatbot] Where would you like this order to
be delivered? [Bella] Home
[chatbot] Confirming 2 promotional packages.
Delivery in 45 minutes. Enjoy dinner, Bella!
Deeply integrated with the business systems, the chatbot knows the customer's name and address,
presents the latest offers that might be of interest,
and creates a smooth ordering process. [Bella] My pizza is cold! I want to file
a complaint and get my money back! [chatbot] I am sorry to hear that. I
am transferring you to a live agent who can help you now.
When the customer is unhappy and wants to speak to a human, the transfer should happen seamlessly.
After being transferred, the live support agent will get the chatbot conversation history and can
start the call informed. But what would this look like with a generative AI chatbot? Would
the customer want to read a chatbot-generated poem about
pizza when placing an order? [Bella] I want to order
two large pepperoni and cheese pizzas. [chatbot] In this vibrant city's culinary scene,
lies a pizza divine, a flavor supreme. Would you like to order a pizza today?
Hmm, that's certainly added personality, but probably not all that helpful in this case.
Ok, let's start over. How can generative AI elevate the customer's experience?
[Bella] Today I'm celebrating my college graduation! I want to order
two large pepperoni and cheese pizzas. [chatbot] Nice to see you again Bella,
and congratulations! No party meal is complete without something sweet! We have the most
delicious tiramisu cake and a new offer – order 1 pizza and 1 dessert, and get a drink for free. Would
you like to take advantage of this? [Bella] You bet!
The next generation of generative AI chatbots can get even smarter and more fluent in understanding
common language, adapting to the customer's style of conversation, and using empathy when answering.
You can optimize the chatbot response even further using generative AI capabilities for search.
Let's see how: [Bella] I have
an allergy to peanuts. Can you confirm that this dessert does not contain any peanuts?
[chatbot] This tiramisu does not contain any ingredients with peanuts. I searched
my knowledge base. You can expand to see all the ingredients and what they contain.
Chatbots with conversational search capabilities can give you answers to the questions you're
looking for, while showing you the source if you want to validate the chatbot's response.
So, do chatbots need AI? Well, yes, it does make chatbots smarter. They can better understand
intent and respond more accurately to questions by learning from its previous interactions,
improving customer experiences. When thinking about generative AI's impact on chatbots,
think about how you can take advantage of creative, conversational responses and when this
technology makes the most sense for your business objectives and the needs of your customers.
Thanks again for watching.
Head to watsonx Assistant to learn more about how to leverage AI chatbots in your business.