Which AI Chatbot Platform to Use? ¶
For individuals and organizations who are unfamiliar with the development of conversational AI solutions, this seems like a daunting question to answer because there are hundreds or thousands of chatbot options available out there.
Investing in a chatbot solution is not a light decision or short-term investment. We would like to share with you two rounds of due diligence that you could perform to evaluate various chatbot options and then decide on which chatbot option or platform would suit your needs the best.
Round 1: Prescreen a chatbot option¶
Before diving into the nitty-gritty details of a chatbot platform, use the following questions to do a quick prescreening of available chatbot options. This process is relatively quick and easy, which should save you a ton of time by quickly weeding out the unhelpful ones.
Does the platform use its own chatbot to serve its own business, ideally in the same solution that you wish to have?
In other words, do they trust their own product enough to dogfood it?
If the answer to the above question is
How do you like your interaction experience with the featured chatbot?
Concretely, ask the following:
- Whether and how well does it understand your free-text input?
- Whether and how well does it address your questions and handle your interruptions?
- Whether and how well does it help you achieve your task?
Keep in mind that this is perhaps one of their better chatbots. It's most likely that if you don't like the interaction experience, it would be very difficult for you to build a chatbot on their platform with which your users would enjoy interacting.
If the answers to the above questions are all positive, ask:
How fast can you use the platform to create a simple AI chatbot yourself?
Just make a simple chatbot to demonstrate the following:
- Make your chatbot ask user an open-ended question (e.g.,
Could you introduce yourself?)
- Ask chatbot a general question before responding to the chatbot's asking (e.g.,
What kind of questions can you answer)
- Observe how the chatbot responds to your input and note what you like or dislike
If the platform does not allow you to DIY such a simple AI chatbot described above, ask:
How long will take the platform provider to do it for you?
If the answers to all the above questions are positive to you, the platform might be worth a deeper look as described below.
Round 2: Compare Chatbot Options by 3 Factors¶
The pre-screening stage could typically help you weed out most of the chatbot options. Assume now that you have 3-5 chatbot platforms to do a deep dive on. We recommend that you evaluate and compare these selected platforms along three factors as listed below.
I. User Experience and Business ROI¶
A chatbot or conversational AI agent is meant to scale out human engagements with a target audience (e.g., universities with prospective and existing students) through a conversation. A key criterion to evaluate a chatbot platform is to assess how well a chatbot engages with a user and delivers satisfactory user experience as well as maximize business ROI, such as improving prospective student conversion and existing student retention rate. When evaluating how well a chatbot option can deliver satisfactory user experience and business ROI, you want to compare available chatbot options on the following aspects:
How well can a chatbot drive an empathetic and productive two-way conversation?
How well can a chatbot deeply understand the psychographic characteristics (e.g., interests, unspoken needs, and personality) of its users from the conversations and use such insights to personalize machine or human advices?
II. Time to Value and Cost of Ownership¶
If not careful, investing in a chatbot solution could become a nightmare as if investing in a bottomless pit that requires constant new investments (e.g., time and money) but with little return of value. To avoid the pitfalls, it is important to deep dive into chatbot options and compare the following:
How much AI training do I need to do up front to teach a chatbot before it can function and deliver value for me?
What kind of customizations are supported?
What resources are required to do the customization (e.g., non-IT subject matter experts, dedicated IT personnel, or professional services)?
How long will it take to make all the customizations?
How do I test, iteratively improve, and deploy a chatbot solution? How easy and fast can I do this?
What kind of reporting and analytics are available for me to access? Are they real-time data?
How can I monitor and maintain or upgrade my chatbot? Will the maintanence or upgrades interrupt ongoing conversations?
III. Enterprise-Scale Adaptibility and Extensibility¶
When an organization adopts a chatbot solution, it is often the case that the organization wishes to build upon the current solution and support new users of the chatbot. Thus it is important to evaluate whether such a solution can be easily and quickly adapted to support new tasks or be extended to support multiple tasks. For example, when an educational institute starts with a chatbot solution to support student recruitment, it may want to extend the chatbot to help prospective students in their application process. Likewise, the educational institute may want to add additional chatbots to help student retention or alumni engagement. To evaluate how quickly and easily a chatbot solution can be easily extended or reused in whole or partially to support new tasks, ask the following:
How quickly and easily can I reuse and adapt an existing chatbot to support a new task?
How quickly and easily can I reuse and adapt an existing chatbot to support multiple tasks?
How can I reuse just part of a chatbot (e.g., Q&A only) in another chatbot?
How can I connect a chatbot to external resources, such as CMS or CRM system?
How can I extend a chatbot with external functions (e.g., my own algorithms or third-party functions such as language translations)?
How can I white-label a chatbot or embed a chatbot into my propreitary solutions?
Build Your Own Chatbot Comparison Table¶
To help your Round-2 evaluation of multiple chatbot options, we have created a set of detailed comparison criteria by the 3 factors mentioned above:
For your convenience, we list all the evaluation dimensions in a table below, supplemented with concrete examples wherever possible to help explain each evaluation dimension. While we use building an educational chatbot solution as an example, the evaluation criteria should be broadly applicable for building any chatbot solutions.
You can also download the comparison template in an Excel file to build your own comparison sheet and evaluate different chatbot options by checking off each dimension for each chatbot option.
Click on the "+" button to zoom in on the comparison table. You can also download the pdf for offline review.
Ready to create your own AI chatbot? Check out these design tips for creating super helpful and user-pleasing AI chatbots to help you scale your business and delight your audience.