Fishbowl’s team of experts has been working with chatbots, specifically Oracle Digital Assistant (ODA) since its inception in 2017. Our expertise has been used to create chatbots with conversational design in mind to enhance the overall ODA experience. Through personalized branding, channels, integrations with Oracle Cloud HCM and Oracle Service Cloud, as well as other 3rd party integrations like Zendesk, we have been able to build and go-live on several successful chatbots with customers in the North American market.
That being said, our success has been earned through some bruised elbows and scraped knees. We have seen first-hand chatbot projects that fail. While such projects fail for different reasons, we have learned that it really comes down to 4 key factors. Factors that occur before, during, and after the project is “complete”. And chatbot projects are never really complete – see number 4 below. Instead, you should expect and want to improve your chatbot incrementally over time. Let’s get started with our list:
1. You can’t just turn a chatbot on and have it work.
- Conversational design is a skill and requires consideration and effort. Natural Language Processing requires knowledge, repetition, and multiple iterations to implement a successful chatbot.
- Each business and their use cases are different, so even out-of-the-box solutions will need some degree of customization. Without customization and understanding the verbiage and business language used by end users, the chatbot will miss intents and misunderstand users.
2. You don’t have good data.
- The chatbot isn’t smart enough to go and find answers on its own. (Well, it is but that’s not necessarily what you want, e.g. Microsoft’s Tay.) The chatbot is dependent on the data you give it, whether it’s good quality or bad.
- Not all businesses have access to the data and metrics necessary for a successful chatbot. Determining how users’ interactions with the bot went, if they finished the interaction, they quit out of frustration, the bot isn’t understanding what’s being asked or is missing colloquial phrases, are all data points necessary to improve the bot. Without them, you won’t know why or if users are even taking advantage of the bot.
3. People expect more from artificial intelligence than it’s currently capable of doing.
- End users seem to think that artificial intelligence is like having another employee that knows everything. It’s not. It’s only as good as you train it to be.
- Because the applications of chatbots are so wide, first phase implementations can be too overarching to be manageable. They can do several things at a barely satisfactory level instead of doing one or two things well, which lowers user confidence and leads to unsuccessful chatbots.
4. Chatbots are not ‘set it and forget it.’
- To have a successful chatbot, it needs to be continually trained and updated with real-world user data. Each company will have different needs, but oftentimes weekly check-ins are needed to ensure the chatbot is running effectively.
- Businesses change often, and so should functionality of the chatbot. A stagnant chatbot can become a useless chatbot.
Building the Best Chatbot for your Business – The Fishbowl Difference
Now that we understand the key factors that determine how chatbots can fail, how can you work to make sure your chatbot doesn’t? Hard work and dedication are necessary in planning a chatbot, but that effort can’t wane once the chatbot goes live.
An ODA’s success is determined by the number of correctly completed interactions, and we have the experience and expertise to help your organization develop and tune ODA to drive to that metric. From an ODA partner perspective, Fishbowl currently sits at number one in regard to the highest number of successful projects and go-lives. Our experience in creating these successful, personalized solutions for businesses gives us a customer reference list we can share with you, as well as use internally to grow and improve future chatbots.
Because we fully understand and focus on the ODA platform, we can help you leverage it to gather valuable insights and data to further improve and update your bot. Between our knowledge and your user data, we can build a chatbot that continues to stay relevant and keeps up with your customers’ expectations. By sharing the understandings of what data is good or bad and how to get more out of your bot, we’re able to create a better bot than you’d get out of the box, or from a team unfamiliar with the specificities of chatbots. Partnering with us also allows you to take a break from the complexities of day-to-day bot-related needs. Leave it to us to handle the updates and maintenance of the bot so you can focus on your core business.
Check out our Oracle Digital Assistant consulting services page for more information.