natural

pping off point. Right now, all you have to do is write a 100% normal TypeScript function without dealing with HTTP, encoding, parameter validation, etc, which is pretty simple compared with what it would take to traditionally create SaaS APIs. > It's funny how people have different interpretation of general availability: "this product is in beta and ready for general use" Anyone can signup and create their own SaaS products, and the service has already been tested by a few hundred developers. Would love to hear how we can improve on our beta's messaging here :) --- We're working on rolling out more example saasified OSS projects over the coming weeks, but here's one that's available today: https://github.com/saasify-sh/saasify/tree/master/examples/t.... It provides a simple, hosted, SaaS version of this OSS project https://github.com/NaturalNode/natural with 80% of any revenue going directly back to the project's OSS maintainers. -- Travis Fischer

answer your question specifically, if following the previous conventions, I would have tried to find some kind of word mapping to find categories from words in the sentence. For example, the question "I can't seem to get my stitching to look neat" or "my crochet hook keeps getting stuck" - it would notice the words "stitching" and "crochet" and decide the questions are related to haberdashery, so ask general questions from that domain (e.g. "can you unpick a little way and try again?", "are you keeping a consistent pressure on your thread / wool?") Of course, this isn't perfect. A couple of people have noted that the duck can encourage you to hack people up (we discourage this course of action and offer no warrantee for any advice the duck appears to present, especially to anyone psychotically inclined). But inter-personal issues are one realm in which this dumb regex-matching falls down frequently - it's very hard to work out that the problem is actually a person, without asking the user directly. That said, this is something that the state machine allows. Sorry if this isn't a very good answer. I've seen tools like https://github.com/harthur/brain or https://github.com/NaturalNode/natural and would love to attempt something with that in the future, but yes - my guess is that it would be slow to train, hard for us to cover all bases, and may not fit into the memory of the client's computer. Alternatively, one thing that we considered and ultimately rejected (mostly on UX grounds) was allowing users to send us their conversations so that we could improve them - again, a manual process, but one that possibly could be automated with a proper AI library and a pre-generated 'brain'! What can I say? That's what v2 is for :)