Ride the 3rd wave of AI & Enterprise chatbot development, like Kore.ai:Lessons from Bruce Wilcox

Building enterprise chatbots is a specialised game. Very few companies across the vastly crowded landscape of chatbot products, platforms and solutions have got this right. Amongst the select few, only the best in the game are spearheading the market with a well thought through approach that can help produce chatbots that truly humanise the conversations.

I am happy to re-share the lessons from AI Guru @Bruce Wilcox in this blog as how Chatscript based approaches fundamentally are more amicable and technically superior in the endeavour to provide a well rounded platform thats complete when it comes to producing enterprise chat bots. Fortunately, we at Kore.ai have always believed chatscript based approach is well suited to meet our deep rooted vision of creating intelligent enterprises through conversational AI. If you are a developer looking to work on the best of the breed conversational AI technologies, If you are a business decision maker working to select the best enterprise class conversational AI platform, look no beyond than these two seminal articles from Bruce and here are some key takeaways from them.

Bruce concludes that the most clever systems leverage both the technologies to get the best of both the worlds. Kore.ai is clearly “the only bot platform for CS… used by lots of major enterprise customers doing conversations at scale”, and "While all other bot platforms depend exclusively on ML, Kore.ai has one that combines ML and ChatScript to support Enterprise bots (serious customers like major banks with millions of users)he writes".

Lessons from Bruce Wilcox:

1)When it comes to natural language, ChatScript scores over Machine Learning .But the most clever systems club both to achieve excellence like Kore.ai's multi-pronged NLP approach. Read here : https://brilligunderstanding.com/ML.html

2) The current crop of bots platforms (places that define bots to performs tasks) cannot help companies build AWESOME Chatbots because they are all based on machine learning (ML), Read more here in Medium.

3) On its own ML is not be a complete natural language solution as it requires too much of training data – roughly 100 training sentences per intent, per his estimates.And large volume ML training data is beyond most developers.

4) ChatScript, an open source rule-based scripting system, takes another approach for natural language. While ML and ChatScript both ultimately do the same thing (they use patterns to classify user inputs), there’s a difference. With ChatScript the human developer requires no external training samples to build a bot. Instead, the developer uses his understanding of language to figure out what the pattern should be, and can write extremely sophisticated patterns concisely.

5)In Bruce’s words, if ChatScript represents the 1st Wave AI (hand-crafted systems), ML represents 2nd Wave AI (machine learning where humans are required to label all sample inputs)

He pitches for 3rd Wave systems that integrate features of the first two waves and go beyond that, learning on their own and in the moment.Because “most serious ChatScript developers use both”. Like Kore.ai.

If you have come this far, time you deep dive into https://brilligunderstanding.com/ML.html and https://medium.com/@gowilcox/machine-learning-needs-help-6a1c8970c758. Don't stop just reading this sign up for a quick demo of Kore.ai's platform here :https://kore.ai/