Making a chatbot is HARD, but this is probably the quickest way into a really, really good one!
January 18, 2020
Making a chatbot is HARD, but this is probably the quickest way into a really, really good one!
Score 8 out of 10
Vetted Review
Verified User
Overall Satisfaction with IBM Watson Assistant
We used IBM Watson Assistant to design and prototype a "proof of concept" chatbot for our senior management to use to interact with a large database of internal business information and markets data (like interest rates and stock prices). It addresses a business need for senior people to be able to interact with large datasets with minimal data-munging skills (and quickly, so not needing to ask for others to provide that data).
- Gives a comparatively simple (for a chatbot/machine learning system!) means to construct a chatbot.
- Very clear framework and component sets
- Important to recognise that creating a chatbot is HARD. IBM Watson Assistant does a great job of making this a bit easier, but it's still a complex and time-consuming experience! I wonder if that can be improved somehow. For example, by applying some smart means to take smart guesses at the form of the data to be used, or a more visual (Scratch-like) interface.
- The prototype was a success, and execs were impressed.
- Hard to identify an RoI, but execs are now much more aware of the data available because of this different way of working with it.
No alternatives considered this time!
Do you think IBM watsonx Assistant delivers good value for the price?
Yes
Are you happy with IBM watsonx Assistant's feature set?
Yes
Did IBM watsonx Assistant live up to sales and marketing promises?
I wasn't involved with the selection/purchase process
Did implementation of IBM watsonx Assistant go as expected?
I wasn't involved with the implementation phase
Would you buy IBM watsonx Assistant again?
Yes