Also: because it's not essential, one gets to adjust to its failures. There's a broad range of queries for which I know Siri will just say "this is what I found online for..."; I tend to just open the browser and use Google's autocomplete instead.
So... I have a problem when the chatbot is trying to perform an essential service, like getting a technician to come to my home because cable internet is not working. Imagine medical triage done by chatbots, jesus christ.
An MTV chatbot that tries to do interactive music recommendation? This could work. Spotify's algo is already very good, but you can't refine "yeah, I wanted something more like X, but a little like Y. And not X exactly" -- just "give me more like X including lots of X".
And nobody gets hurt by a bad song recommendation.
But, what's really interesting to me is that Alexa has surpassed that level (at least in my household). So that for routine things, it's not a novelty to use it, but an actual improvement.
This is still obviously for non-essential services like music, games, weather, etc. but it's also reliable enough to handle things like turning on/off lights in awkward spots.
You've just learned the language she speaks.
If only that were true! The trend is to ask for a little bit info at a time, then take you to the next page where it asks for other info, and so on. You don't see at a glance the whole form anymore.
I resort to filling in fake info on sign-up forms, order pages, employment applications, airline/hotel reservations, etc., just to find out what questions they'll ask so I can decide whether to refuse before I tell them anything.
And also to find out key information they tell you only at the end (sales tax, shipping cost, etc.).
People see a fleet of fields and just go. People see 2 fields and they tend to just enter in data. Even if they leave and come back, mobile apps and websites can much mor easily checkpoint this (digression: I think it's easy to checkpoint a form but lots of people don't and only web toolkits make it drop-dead easy to do).
Sorry you're on the right hand side of the computer competency power law distribution.
Worse yet, they have very similar (except for color) buttons for "Log in" and "Sign up". Often if you have bad internet and the last layer of the page hasn't loaded yet, you don't know which button to press.
That's a good strategy, particularly since there are websites that send everything you type, even if you erase it or don't submit.
Compare and contrast with data mining the logs of call centers into RNNs and hoping for the best. A fun exercise here is to take one's SMS logs and do the same. In my experience, one will achieve an amazing Max Headroomization of one's cliches and trademark expressions, but little else.
When confronted with a voice menu system, I used to scream "OPERATOR! OPERATOR! OPERATOR!" at the top of my lungs and bang on the 0 key repeatedly until I got connected to a human. Recently, I've noticed they hang up on this behavior and even force one to wait through the entire braindead list of choices before allowing pro-users to bypass all the inanity because, after all, one must "listen carefully as our options have changed!"
I've definitely had them ignore any sensible operator prompts, but actually hanging up? That's a step beyond. Care to name and shame any offenders?
(I've always enjoyed the claim, and once or twice believe I've observed the behaviour—though I am sceptical—that a lot of these systems scan for obscenity, and route to an agent. When I get a robocall while I'm out walking (phone for audiobooks), I always curse at it for a while, just in case. Even though it almost never gets an agent, it's a good stress reliever!)
- That people that spam zero should be hung up.
- We could do a fake accent if we could maintain it through the whole call.
- After they had deleted the feature for support to activate your new device as a cost saving measure we were to point users to the proper procedure to do it themselves on the web and tell them that feature was broken despite the fact that leads could still do this.
- To make up fake things we had in common to establish a relationship with the customer so they would give us better surveys.
Customer service is not their strong point.
But it did feel really weird hearing the automated system say "that is not a valid option. goodbye" and hang up on me. No indication that I could call back during certain hours to reach a human.
The user is telling the menu tree that those who programmed the tree didn't include this use case or that poor descriptions routed the user to the wrong area. Have a human cleanup pass.
Often I do end up pressing 0 when I have a strong suspicion that I'm going to need to speak to a human to get my actual problem fixed and am pretty sure nothing's going to change that.
I absolutely despise chat and voice for any kind of trivial task. I want a UI. Chat and chat bots are annoying. Voice in any form if infuriating. Having to actually call a number on the phone for any reason always sends me into a minor little rage. "Oh, you have to f'ing call for it... sigh." Why would I want more of this kind of experience? Maybe a few people do but I can't see it being a Big Thing(tm).
I really do not want an Internet-connected fridge, stove, light switch, or microwave. When I buy such things I look for non-IoT-encrusted versions since those are going to be more reliable and are not going to be conscripted into a botnet or spy on me. IoT features in these kinds of products deliver nothing of value to me. I also really do not want DRMed food. That includes newer Keurigs. There is a healthy vintage Keurig market on eBay for a reason.
VR still seems like a fad or a niche product for certain subsets of gamers. There's some market for it but it's no "E-Commerce," "Social," or "Mobile."
It's sort of funny to see the SV investment culture producing so many solutions in search of problems after hearing that same culture lecture against this practice for decades. "Do the market research first!" "MVP MVP!" etc. They're not following their own advice.
And now I see they're automatically opening Messenger when you visit someone's page to get you to message that business for... I'm not exactly sure what reason.
So instead of pouring endless money into chatbots, allow people to do whatever they wanted without involving CS. Provide good, up to date and easy to find documentation and a web interface if the task needs data entry (porting your number, changing your billing details, etc). This will reduce the load on your CS which means you can now bring this back in-house and no longer rely on an outsourced disgruntled workforce.
If you can't be bothered to write good documentation then you won't be bothered to feed useful information into the chatbot, which is way more clumsy than a searchable manual anyway.
And even better, the pizza joint can update the conversation with status updates, special deals if you so desire, and you automatically have a history of previous orders that you could simply repeat at a later time.
A chat bot strikes me as the perfect UI for these types of things, and at this point, with Messenger, Messages, and Telegram supporting all this, a large number of your users already have 'your' app installed!
- I'd like to order a pizza.
- Great! What kind would you want?
- I have no idea, what kinds are available?
(Silence while somebody asks themselves if they really want to dictate 100 different kinds of pizza for you)
- Do you have $POPULAR-KIND-THAT-IM-ALREADY-TIRED-OF-EATING?
- Yes! (Relief by not having to dictate all of them)
- How much is it?
- Oh, it's $$$.
- What?! $$$ for a single pizza?
- Yes, that's a MOST-EXPENSIVE-CATEGORY-OF-PIZZA, it's totally not the simple pizza you were expecting from the name.
And so it goes.
That's my thinking exactly, and while I agree with the article, I feel it would've been much more interesting if it explored what kinds of ways chat interfaces and bots can be used.
The first example mentioned is illustrative:
> Press 1 to report missing credit card... Press 2 to report a fraud... (...) Press 8 to activate a credit card... > It's far from an enjoyable experience. When you call them and hear a recorded voice, you can tell that your call is going to take a while. You also know that there's a high chance you'll end up talking to a real person anyway. > Chatbots are no better than these robots.
I strongly disagree with this. The problem with this interface is not the 'robot' part, the problem is that you have to patiently listen to a robot describe the options before you get to choose.
If I could have a chat with a bot that immediately provides me with an inline keyboard or a list of options so I could choose an option right away, or type it out, or perhaps even type out a command-line style multi-argument command, I'd prefer that over pretty much any other interface, including clicking around their clunky website. And most chat API support inline keyboards that can even 'replace' themselves, allowing for a pretty powerful mini-ui.
The problem, as I see it, is trying to make it natural and adding all sorts of NLP and 'human' elements. Let bots be bots and at most augment them with these things.
I truly believe that chat bots can end up being a 'CLI for non-geeks'. They're not appropriate for everything, but what with custom keyboards, inline keyboards, and other inline doodads, I wouldn't be surprised if they'll end up being successful even for the non-CLI or non-chat type use cases. Everyone has Telegram or Messenger or Messages, and 'everyone' seems to be moving to their phone or phablet as a primary interface these days. They don't want you shitty custom app, they hate your clunky barely-mobile website. But their favorite chat app has authentication, essential UI stuff, 'native' services (location, etc.), and push notification and sync built in, so why not use that?
For a growing number of people around me, the 'de-facto' chat interface is the one they have open much of the time (plus snapchat's weirdness, perhaps). While I feel the current interfaces are still lacking for these non-person-chat use cases, already now I find that they can be much more useful than people realize. It wouldn't be too difficult, I suppose, to optimize these chat apps to handle various bots better (and perhaps WeChat already figured this out well enough?).
"You are in a maze of twisty little passages, all alike. There is a CUSTOMER SERVICE REPRESENTATIVE on the ground."
Also, there's a need for a more declarative, high level programming language to describe how you can interact with a bot. Defining them as trees or graphs isn't flexible enough. I've had promising results from experimenting with concepts from Ceptre (https://github.com/chrisamaphone/interactive-lp). Fortunately there are a lot of startups experimenting in this space, I think we'll see the most effective practices replicated quickly.
Actually, maybe 'unnatural' is not the quite right word, as I have had some human customer service that is no better in this regard (or perhaps they were actually some of the better chatbots?)
(provided the site FAQ's are actually frequently asked questions and not - as often happens - a bunch of questions that the original website developer jolted down because he/she imagined they will be asked and that noone actually updates with "real" questions asked by customers).
So you get to talk with a human, but very often this human is either clueless or cannot really do anything about the issue at hand. (not of course fault of the human, but rather of the way he/she was mis-trained or because of directives coming from the company)
>manage to escalate to a higher level of support
It's not that easy on many support Call Centers in my experience, not before having gone through the checklist with a number of unuseful suggestions (already tried because listed in FAQ).
First thing to type when you get a chatbot support is "I would like to speak with human". That usually works.
Examples of chatbots that do work
Nuance's Nina https://www.windstream.com/Support/
Jenn (unknown who is behind it) https://www.alaskaair.com/
Our James https://master.boost.ai/
James: My name is James and I can help you with bank and insurance questions. Write to me in either Norwegian, Swedish, Danish, Finnish or English.
Me: Hey, I am French, and am living half in the US and half in France, do I need to purchase insurance in the US?
James: We offer a full range of insurances to meet all your needs.
James: Select an option: Cars other vehicles Home insurance Travel insurance Health insurance File insurance claim
You: Can I get cheap internet without tv and phone?
Wendy: To inquire about or change your current service plan, please contact a customer service representative at (800) 347-1991, or find us at your local retail store.
To locate a Windstream store near you click here.
It's just a search engine with a worse user experience. Reminds me of Ask Jeeves, but more patronizing.
If you meant who built it... http://nextit.com/work/alaska-airlines
James: I´m happy to help you regarding savings account.
James: Select an option: Order account Change account Other inquiries
Option 1: Links to google.no without a search term.
Option 2: "Chat with one of my colleagues in online bank, or call us at 00000 if you would like to make changes to your savings account."
Option 3: More options that lead to phrases such as "Interest rate on savings account is X %."
Sorry, but this just cements the fact that chatbots are utterly useless.
Me: what are some good tourist destinations?
Jenn: I am not sure I understand your question.
Me: where can I fly to cheaply?
Jenn: I am not positive that I understand what you are asking.
Me: do you have any package deals?
Jenn: Takes me to deals page; but I was looking for package deals including hotel and car
They will get better and eventually get better than humans. It's a new use of technology, give it time to improve.
I already know of companies using AI to adapt to customers like this article says chat bots don't do. It's cutting edge but it is out there.
I'd rather talk to a chatbot than:
- the same (or worse) bot over a phone
- someone who only vaguely speaks my language
- nothing/nobody at all
- someone who speaks my language but spends 10 minutes and 30 "thank you"s to tell me they can't accomplish what I need
The only form that wins out is a living person who is well-trained and speaks my language well. Most companies already won't provide that.
Why is it a new use of technology? I seem to remember chatbots being around in the 90's... or am I imagining things?
Of course, they sucked, and people said "they will get better and eventually get better than humans." I don't see what has changed in that regard.
Maybe the assertion is still true, but despite advances in NLP and other areas of ML, it hasn't seem to have improved the bots, or their associated customer experience.
I'd just like to ask that if anyone is seriously pursuing chatbots, beyond just helping businesses or consultants sell the 'next big thing', I'd really, really love to talk. My email address is on my profile page.
However the current status is not so grim. In a different application domain, a customer of mine uses a chatbot to collect leads of credit requests. Their very basic chatbot converts much better than their form. The difference is so big that it pays for the extra work to manually extract data from those conversations that went to the end but we can't automatically get all the information from (funnily formatted dates, addresses, etc)
Have you ever used one that emits "typing" sounds in to the phone? AT&T started doing this some time ago on their small business wireless support line. I jam zero until it says, "Ok, enter the number you are calling about", I enter it, and it says, "Ok, let me look that up for you", then keyboard taping sound... I can't even describe my reaction the first time I heard it. So, so stupid.
The real problem I see is that the last decade of user experience improvements that work well on the web don't really translate into a chat, as an industry we're hopelessly bereft of best practices at this point, and our users notice this and experience it as the frustration of having no idea what to expect from a bot. The title article and comments cite a lot of good examples.
NLP and other applications of machine learning will make bots better at delivering correct answers, but making bots feel not-horrible around the edges is about user experience design. Here are some suggestions that have helped me a lot.
* Design for failure first
Just like mobile-first design gets the brain out of the pattern of tacking on mobile interactions as second class citizens, failure-first design focuses on the primary experience the users have of your bot, it not working. Don't delude yourself into thinking that your NLP intent parsing is going to result in more hits than misses down your happy path to user delight. A human will always sidestep your intended flow by accident, and that human will form judgements about your product based on it's ability to gracefully recover. Luckily the bar is incredibly low here.
* Be careful with conversational niceties and over-humanization of tone
It's easy to think that friendly banter and emojis can help personify a bot and smooth over the above-mention failure paths, but the novelty of these wear off quickly for a user, and the user is likely to experience more frustration if the conversational tone doesn't match their frustration. It is also extremely easy to end of in the uncanny valley when using friendly conservational copy in the bot messages. Repetition of a robotic message feels benign-if-annoying, but repetition of a cute emoji-laden phrase can feel very off-putting.
* Fall back to being a CLI with visibility and helpers
If you've ever been stuck working with a bot, you know that all you want is to know what it can do, and how you can get it to do that thing. If you notice the user is in a failure state through keyword matching or repeated failed routing attempts, fall back to a high-visibility list of actions. Having quick-action buttons can make this even smoother.
* Train the user on consistent hooks and keywords.
When speaking in a human conversation, utterances of 'stop' or 'wait' are almost always respected as context-independent keywords that escape or pause the context of the conversation. If I asked you what you wanted for dinner, and you responded 'stop', I wouldn't try to figure out what kind of food that was. In my project, 'help' 'quit' and 'back' are all respected as keywords, and every context of the conversation implements callbacks to respond in context to each of these.
* Ask a lot of questions that are easy to answer
Handling raw language is super hard. Routing language into a finite set of options is a lot easier, plus humans feel listened to when asked for clarification or if they have been understood correctly. When taking user input and routing to an action, ask for yes/no confirmation, and provide options like "This is totally wrong". Opportunities like this could be great to collect data about how users are stuck to improve on the experience. It's also validating for the user to feel like they can specify that they were not heard correctly.
It then compares it to a personal agent that actually has a similar model and the worst voice recognition and search precision of the current crop agent software which... isn't even really the same kind of software?
What is this article even trying to say? Poorly written bots are bad, well-written agents are good, and voice interfaces aren't as bad as people make them out to be?
Cool.
