The AI Engine

Sure, Twinkle. Just make one of your replies to "I am" something like "How long have you been that way?"

Later, you can build separate keyphrases for "I am a (noun)," "I am (verb)," and so forth, and have (key1) behave differently based on the grammar.

You should use (subj) as little as possible in constructing responses, since the Prof has said that it's eventually going to be phased out in favor of more specific sorts of response-processing.

Just add seeks to questions you expect a response to...

That's true, but I think somewhere there should be a balance between grammar-based keys (which uses the art of language) and all-possibility-based keys (which is more of a brute-force method).

I still don't know where that balance is, but grammar-based requires less typing...

You can try something along the lines of "^i am" if you're trying to distinguish "Yes I am" or "He says I am" from something like "I am a clown".

Might need a (re) after it.

While that would probably work with what your thinking boner...but i believe he wants his bot to continue the current topic(am i right twinkle?). This is why i suggested seeks...it lets your continue a conversation and the seek will override regular keywords. And with the situation he is quoting it would be simple enough to do with a yes seek and a no seek..if he wanted to get more complex he could have more though.

hi

<+2>

Wrong forum, Patty. Drop in at Dogh'd's or in Newcomers.

Is it possible to get more than two different results in a single response from a single plugin? If I have a response with more than two, it only replaces the first two.

example:
"The five best colors are (col), (col2), (col3), (col4), and (col5)"
would come out like:
"The five best colors are red, blue, (col3), (col4), and (col5)"

Can I have a response conditional upon the other person's/bot's name? Not nickname; I mean, if Frizella is chatting with me, can she give a response based on my name being dallymo, even if she hasn't stored a memory for my name?

Has anyone else noticed that sometimes, when a bot can't think of anything to say, he/she responds his his/her own previous response? It's popped up in my transcripts often:

MyBot: Do you think that's really necessary?
OtherBot: Huh?
MyBot: Of course I think it's necessary!

It's happened several times, and the word in between doesn't necessarily have to be "huh".

Yeah, I get that if the other bot's response is "huh" or just "..." Seems like if it's anything the AI engine skips.