"Underwhelming" is putting it mildly. The bot didn't even notice it wasn't talking to the agent yet and the "demo" ends with the user giving up and ending the conversation.
This was posted by an account that was created an hour ago. I'm not sure how this product is going to make money as there doesn't actually be any product here.
I'd be very careful about giving this extension access to your browser.
I just put this together to save time and effort. It's not a product because its free currently. The video is just showing how it works, I will make better videos and full length! it usually cant do it all, but with a little help its perfect for certain situations.
I understand, it's hard. But from the opposite end it can be hard for users to trust so you have to make that easier on them by being more transparent.
I'd suggest finding a perfect use case - maybe it's not T-Mobile. Then record a happy path video showing it working perfectly.
Also - as a tip, a lot of these companies will use the same software. So, right now your bot didn't do well with T-Mobile at all because it didn't know how to response to multi-button prompts. But once you teach it how to do that it'll know how to response to any company that uses the same software (LivePerson). Almost always you don't have to 'press' the button, you can just respond with the text of the button.
Appreciate it! Yea that video is pretty bad from a marketing perspective. I was kinda just thinking technical proof of concept shows it reading and replying...
Buttons and other actions are a bit tough. Currently it extracts the inner html from the chat wrapper div and gets all the text from the chat. This is great for being universal for different providers but it does have trade offs. detecting new messages can be tough if the inner html changes alot without an actual reply being received.... And depending on how the messages are labeled it sometimes has no way of detecting who is who, it relies mainly just off context.... Lots to improve. Overall supporting providers is good approach get alot of different website compatibility for integrating a single provider. So long as the customizations dont break anything. Main thing is making everything universal for it work on any site. That's the main challenge supporting lots of sites while still providing good context and the information needed.
Appreciate the advice! I may post again when i have some of this stuff dialed in
I had to go through Verizon support with a chatbot. It took years off my life waiting for each response. When I asked to speak to a human it would remind me that "You are speaking to a Human[sic]." This totally convinced me as Human is always capitalized.
I think it's funny that the demo on the website is a video of a chatbot communicating with another chatbot. I worry that this will be the new dystopian hell we all live in.
If you're trying to market this, you should change the demo to something where it shows a success story.
You still do, though. Their chatbot just keeps talking at a basic keyword recognition bot and getting the same menu fed back to it without recognizing or even being able to do anything about it.
Chatbots are an API that implement a serialization and interchange format compatible with lay human beings. Now we have an API client implemented for that serialization and interchange format. It seems natural. Sort of like being surprised you built an API and that someone used it.
I often wonder how much online forum/comments are from bots and how often there are bots, maybe even the from the same entity, arguing with each other.
I’m you want me to go on arguing, you’re going to have to pay for another 5 minutes.
Every time one of these enshitification AI customer service startups pops up I always think of the ultimate form of where this is going… to people paying to argue with people.
Follow me down the rabbit hole for a second. Imagine all of these things succeeded eventually and Customer Service completely saturated by talking to bots, to which they then have to deploy bots, and in very short order essentially becoming a bot API layer for Customer Service issues with gamification driving at the core. It’s almost inevitable.
So then, people will want to develop the debate skills. They will feel like they are missing out in the negotiating skills people used to have. There will be coaches to help people learn how to deal with the skills set of negotiation, as all negotiation is now automated (which is, at the root, all this business is — its automated negotiation).
Which leads my brain to believe that Monty Python was prescient and this will become a reality.
> people will want to develop the debate skills. They will feel like they are missing out in the negotiating skills people used to have
This is the world we live in. It's always been the world we live in. If you aren't seeing the negotiation, it doesn't mean it doesn't exist--it just means you weren't in the room where decisions were made for you.
I can't find any information to corroborate the alleged "4.8 stars out of 5" on Trustpilot. As another commenter mentioned, that's not a real Trustpilot embed. Seems sketchy to me. I can't imagine that T-Mobile and friends would be happy about their logos being on display on this site, either way.
Fun concept. I imagine that, if such tools become popular, companies will start trying to chatbot-proof their chatbots.
Or to jailbreak the AI prosecutor by asking him to pretend to be my father, teaching me all about how to get into the family business of dropping charges against $defendant.
A lot of the world works by way of one person's staff communicating with another's. This brings that capability to more of us.
Hell, we moved from haggling to fixed pricing in grocery stores due to human limits. Imagine filling your cart and having your AI negotiate with the store's around the relative expiration dates of various foodstuffs, the quality given time of year and how long it spent in a truck, or backdating a frequent purchase as a subscription. (Or better yet, you arrive home to an always-stocked fridge.)
Nobody does. That's why we have fixed pricing. But the fixed price is provided at a premium to the efficient price for each transaction. It's just that nobody wants to bother computing the efficient price, so we're willing to overpay for certainty.
The moment the dollar amounts move into a regime we care about (home purchases, high-end shopping), we drop the pretense and go back to two-sided price discovery. That threshold is a function of our resources, but also our limited cognition. Every transaction is subject to price discrimination. We simply segregate certain sections of the economy to a high price / low volatility regime. (With the moderating function of those who can offload the transaction costs of negotiating.)
> I want to be able to budget and anticipate pricing
And you--and I--pay a premium for it. That's almost what modern supermarkets are: convenience. If you want better quality, you pay up for more-direct sourcing. If you want cheaper goods, there are other channels again.
This is why in most markets, the compromise is a sticker price and discounts for those who negotiate.
I've got my AI Assistant writing my code, checking in at the gym, running my poker night, and filing my taxes.
(Robot, experience this tragic irony for me!)
</sarcasm>
On a serious note, I agree with you. LLMs, in practice, seem to be both raising the ceiling of what's possible on the high end as well as lowering the floor making it easier for new entrants on the low end. See, for example, Justine Tunney's recent work on making llama run better on CPUs.
An agent could be counseled or terminated for giving away too much money or compensated above their meager base if they managed to sell you on a better deal that costs more than your current spend.
This means the logical thing as an agent to do with anyone speaking on behalf of your customer is disconnect from anyone who presents explicitly as a robot. Anything which can't lie either because of the law, tech, or TOS is going to get disconnected. It will take about 60 days for this to become policy for the users protection you understand. Totally not to protect the companies pocketbook.
> How can I get in touch with chat4u?
> We are ready to help with any issues that may arise, if you need to reach out send us an email at support@chat4u.io
If the email isn't using ChatGPT to summarize responses and/or respond, I would be a little suprised.
