I’m on the online chat support with Palm right now trying to figure out how to get my Treo 650 to work in China and collect more information for my Cell phones in China post. As with other online help systems I’ve tried – almost always with regrets – I’m finding the online chat experience very frustrating and inefficient and time consuming. Inefficient enough that I’m able to do this blog post while chatting, and learning that the technician appears to have far less information than I’ve already collected about how to get my Treo to work in China. You’d think this would be a simple question and they’d have a nice FAQ but no, he’s sticking with me which I sort of appreciate, but so far all I have learned is the the Treo wil work in China but he’s not sure about the Sprint Network. Unless I’ve missed something he’s missing the whole point here – you need unlocking and a SIM card which you normally purchase in China.
The failure of these chat support systems is really interesting because it seems like it should be a good way for a single support person to handle dozens of questions. For some they’d know the answer immediately and send people on their merry way, while more complicated questions could be answered by using their databases, FAQs, and internet. Yet generally I find that a phone call is more effective in drilling down to the issue and even faster unless you are on a very long hold.
OK, after over 30 minutes I have absolutely NO information I did not have before. A total waste of time again:
Joe Duck 
I assume this is a transcript of an online ‘chat session’ wherein ‘Silas’ is a computer program, not a real person at all.
Yes a transcript but I think Silas was a real person.
Well, I’ve re-read the transcript and still think that it sounds like a chat session with an artificial intelligence program, not a live person, but since you were the one who actually experienced this chat session, you probably know best.
I have found that chat help people tend to seize upon the most commonly encountered reasons right away.
If it were a bot, I’d think it’d have better grammar, and I’d expect to see a search tree in action, or at least some entertaining nonsense 🙂
FG what you see is the entire exchange – now you’ve got me curious. Silas certainly sounds like a MACHINE, and one from a dystopian futureworld to boot!
But I agree with Tommo that we’d actually see better grammer and more logical interaction with a machine session.
If it were a bot, I’d expect see things like “You want to go to China? Why would you like to go to China?” 😉
Sorry, couldn’t resist. I’ve had equivalent bad experience both on the phone and via chat. On the one hand, phone *tends* to give you the same answer but faster – on the other hand during a chat it’s much easier to be doing other stuff and checking the screen every now and again. I think I pretty much agree, most of the time I prefer using the phone.
Its odd perhaps how we view this transcript. And can accept the existence of a person at the other end of the phone line whose performance is disappointing but are less inclined to accept the existence of a ‘bot’ at the other end of the line, particularly a bot that is a poor performing one. Why is it that we expect a bot to be “better”? Perhaps its not yet learned it job and its knowledge base is low?
Grammar? Does Joe’s use of the word ‘grammer’ prove he is human? Wouldn’t a bot misspell the word too if it was a poorly engineered one? Is quality of the interaction the test for human versus bot?
Irrespective of whether this particular transcript is that of a human or an artificial intelligence program, I wonder why people prefer to deal with a voice rather than with displayed text? One airline company yanked out an automated lost-baggage system and put in a human being who performed less well but sure dealt with frustrated travellers better.
I guess the main reason it doesn’t look like a bot to me is b/c it doesn’t look like the bots I programmed 🙂
It’s certainly true that a bot with an ungrammatical repertoire will produce ungrammatical output. I presume that QA would weed that out at a place like Palm.
Wouldn’t a bot misspell the word too if it was a poorly engineered one?
Maybe, but this brings up an interesting aspect of machine “intelligence” that I think has very profound implications for the long haul Unlike a human, the bot will only need ONE correction of a grammer mistake and then it’ll be correct for the next 1000 years. When the machine is capable of “recursive self improvement” it’ll be able to study grammer and fix itself.
Why hasn’t this happened yet? Because programming that level of activity is a lot easier for me to talk about than for guys like Tommo to actually do! But get cracking Mr. T cuz we need them thinkin’ puters ASAP!
Pingback: Ramona and Jenn « Joe Duck
I THINK IT IS A BIG WASTE OF TIME TO USE CHAT LINES BECAUSE THEY DON’T KNOW AS MUCH AS WE DO OURSELVES.