SageTalk

Live chat platform for the age of automation

get it

SageTalk is the power of Automation and the historical greatness of Live Chat. All in one product.

Reviews

  • Lion GoodmanCEO, Executive Coach, Teacher
    Pros: 

    Automates standard and repeated question answers for customer service reps, reduces costs of customer service department and function.

    Cons: 

    It may reduce the customer service workforce, which is good for the company, not as good for the reps. The CEO of Sage has a plan...

    I have been shown a demo for this product - it is quite amazing - it learns by watching the flow of questions and answers, plugging into already existing customer chat apps, and taking over the most common Q&As.

    Lion Goodman has used this product for one day.
  • Amir ReiterCEO,CloudTask
    Pros: 

    Automates Customer Support

    Cons: 

    we will let you know when we find one

    Great Product.

    Amir Reiter has used this product for one month.

Discussion

You need to become a Contributor to join the discussion - Find out how.
Tom LevMaker@tkornblit · Founder
Hello Product Hunters! Tom here, Founder and CEO of Sage AI, makers of SageTalk. After 2.5 years of listening to market needs and iterating on product towards our vision, today our entire team is extremely excited to be releasing SageTalk to the public: Our company-wide mission is to be able to replace 100% of customer service chat volume for any organization by 2020. We believe this is the direction the world is going in and we are excited to contribute, and help organizations shift into this better, more optimized way of working. For teams already using Live Chat, our product offers an upgrade for medium to large sized customer service teams that understand the value of automation and eliminating drudgery. Key Features include: - Analytics - Brain (Training the bot) - Testing (Testing the bot) - Live Chat (Our own Live Chat functionality) - Chatbot (With a seamless handoff to Live Agent team) Looking forward to hearing your feedback! Thanks, Tom
Aaron Cohn@aaron_cohn · Head of Community, Vervoe
Totally makes sense...for common requests, smart bots can do a really awesome job. That said, there's nothing more frustrating than dealing with a bot that doesn't understand your issue. What's your process for kicking it to a human?
Tom LevMaker@tkornblit · Founder
@aaron_cohn Great question Aaron, and thank you for raising it. The process for kicking it to a human is part of our patent-pending design. The process is as follows: 1. You ask a question to the bot 2. Bot checks it's brain and sees if it has the answer 3. If it has the answer, it will return to it the user, If it doesn't, it will give you the option to instantly transfer to an agent. The handoff is seamless, and this exact feature is the reason why it made sense to build this product in the first place. We didn't see any product in the space that was doing the hand off right. And we found that with the handoff missing, it was unlikely for any Customer Service teams to adopt the AI into their stack. Turns out we we're right - as today, the only companies that have a working Chatbot + Live Chat solution are big companies like Amazon or Apple, which built their own custom solutions. Hope that helps Aaron, Tom
Aaron Cohn@aaron_cohn · Head of Community, Vervoe
@tkornblit It does!
Juhan Kaarma@juhankaarma · Co-founder @www.getweps.com
@tkornblit @aaron_cohn Very interesting product. A common issue with NLP like this (that we're stuggling with ourselves too) is that the bot mis-identifies the intent of the user so even though it should trigger the handoff, it doesn't cause it thinks the user asked a question that matches one of the intents, even though it doesn't. I'm wondering, how do you deal with situations like those?
Tom LevMaker@tkornblit · Founder
@aaron_cohn @juhankaarma Thanks for the kind words Juhan! Great question! Our solution to this problem is we built a technical abstraction we call the Brain. The Brain's primary function is to allow a human to train the bot in a very straightforward way, leaving all the complexities to the AI (Intent Matching) Engine, and keeping the user experience very clean. The way you train the bot in our software is as follows: Say you wanted to teach the bot how to answer a question about where your company is located: In SageTalk's Brain, you'd create a topic. As one of the fields in the topic view, you would add the answer to this question, which in this case would be: "We are located in the heart of the wonderful one and only San Francisco." And then you'd add Expressions (meaning different ways you can express the question). In this case expressions could be as follows: 1. where is your head office 2. where is sagetalk hq 3. where is sage ai located 4. where is your main office located 5. where is your company located You'd then save the topic, and then the bot would add all of this information into it's Brain (Massive NLP Search Index). This is also part of our patent-pending design, and what makes our product so unique. Hope that helps, Tom
Harry RaymondHunter@harryraymond · Building Smalltalk, Product Hunt NYC
Very cool product. Could see this being a big help reducing support tickets. Do you have plans to add additional channels like Messenger or SMS?
Tom LevMaker@tkornblit · Founder
@harryraymond Hey Harry, Thanks for the question! We already support Messenger and planning to support SMS shortly.
Trevor OwensPro@to · CEO, Javelin.com
Congrats @tkornblit!
Tom LevMaker@tkornblit · Founder
@to Thanks Trevor!
René Be@rene_be
Very useful product! I remember the times when I wanted to be present on chat for my users, and I knew what to answer, but I didn't have a way of automating it like this. I can imagine many companies can focus their customer service on more important and difficult questions, while having this smart pre-screening, saving a lot of time. Thanks for bringing this to the world!