Our support ticket volume was overwhelming,so we built an AI to handle 80% of it
1–10 of 11 posts
Re: Our support ticket volume was overwhelming,so we built an AI to handle 80% of it
#2SR, co-founder of Kasp here.
The title isn't an exaggeration. A few months ago, i was working as full-stack developer for e-commerce company on the support ticket solution part. and I were drowning in support tickets & enquires day by day.
We were spending 6+ hours every day answering the same repetitive questions about pricing, features, and basic "how-to"s. It was killing our productivity and ability to build.
We looked at existing chatbot solutions, but found they were either glorified keyword-finders that frustrated users or complex enterprise tools that cost a fortune and took weeks to implement. So, we built our own solution. It's an AI chatbot that you can train on your own knowledge base, docs, or even just a simple FAQ page in under 5 minutes. Existing RAG solutions are not very good at complex answering we tried hundreds of different RAG techniques but most of them are good for simple questions and doesn't understand the context of the customer perspective.
The key is that it uses RAG with our our custom implementation on top to improve the accuracy and speed to find the actual answers within the customer context so users trust the responses.
For our own project, it's now accurately handling about 80% of inbound queries, freeing us up to focus on what matters.
We've just opened up the waitlist today and would love to get this community's feedback on the concept and the landing page.
Link: https://www.kasp.chat/
Happy to answer any questions Thanks!
Re: Our support ticket volume was overwhelming,so we built an AI to handle 80% of it
#3Customers might be delighted, as well. I look for that trio.
Said as a former sales engineer.
Re: Our support ticket volume was overwhelming,so we built an AI to handle 80% of it
#4Hey HN, SR, co-founder of Kasp here. The title isn't an exaggeration. A few months ago, i was working as full-stack developer for e-commerce company on the support ticket solution part. and I were drowning in support tickets & enquires day by day. We were spending 6+ hours every day answering the same repetitive questions about pricing, features, and basic "how-to"s. It was killing our productivity and ability to bui…
The address doesn't resolve for me (possibly my PiHole acting up), but our primary support is email-based, currently through Hubspot. Given the name I presume this is purely a chat bot? Makes sense, just asking.
Re: Our support ticket volume was overwhelming,so we built an AI to handle 80% of it
#5Meaning no disrespect, but wouldn't effort put into making pricing, features, and basic "how-to"s a lot more accessible and useful pay dividends? Customers might be delighted, as well. I look for that trio. Said as a former sales engineer.
Re: Our support ticket volume was overwhelming,so we built an AI to handle 80% of it
#6Hey HN, SR, co-founder of Kasp here. The title isn't an exaggeration. A few months ago, i was working as full-stack developer for e-commerce company on the support ticket solution part. and I were drowning in support tickets & enquires day by day. We were spending 6+ hours every day answering the same repetitive questions about pricing, features, and basic "how-to"s. It was killing our productivity and ability to bui…
We're in the B2B space so not that much trivial pricing questions such, but do have a fair share of repeat questions that could have been solved by reading our docs. The address doesn't resolve for me (possibly my PiHole acting up), but our primary support is email-based, currently through Hubspot. Given the name I presume this is purely a chat bot? Makes sense, just asking.
this is not an normal chat bot we have 100s repeated question and find a pattern within them so based on the documentation we can predict what kind of question that the user can possibly ask so based on this we have implemented our own custom RAG solution that has high accuracy with relevant context with minimal latency.
also we have human in loop concept in the upcoming update
Re: Our support ticket volume was overwhelming,so we built an AI to handle 80% of it
#7Earlier quoted context omitted.
We're in the B2B space so not that much trivial pricing questions such, but do have a fair share of repeat questions that could have been solved by reading our docs. The address doesn't resolve for me (possibly my PiHole acting up), but our primary support is email-based, currently through Hubspot. Given the name I presume this is purely a chat bot? Makes sense, just asking.
we have FAQ section with a brochure in each category of the product but most of them want to clarify specific them about their use case (context) so they contact the support to verify this works 100% for their use case. this is not an normal chat bot we have 100s repeated question and find a pattern within them so based on the documentation we can predict what kind of question that the user can possibly ask so based…
Sounds interesting, will check it out from another computer.
BTW, figured out it was some DNSSEC issue causing the domain not to resolve, getting "NSEC(3) missing" in my PiHole, which seems to be correct[1]. Guess I should have taken the hint[2].
Re: Our support ticket volume was overwhelming,so we built an AI to handle 80% of it
#8Meaning no disrespect, but wouldn't effort put into making pricing, features, and basic "how-to"s a lot more accessible and useful pay dividends? Customers might be delighted, as well. I look for that trio. Said as a former sales engineer.
we have thousand of product each have slight different variation for each product ex: Product EZ01 has this feature were EZO2 have a different feature in our website we have a brochure to see all the details but most of the user don't want to download and read they just open the Support and ask questions about the product and detail that was the issue we are facing
Re: Our support ticket volume was overwhelming,so we built an AI to handle 80% of it
#9Re: Our support ticket volume was overwhelming,so we built an AI to handle 80% of it
#10Meaning no disrespect, but wouldn't effort put into making pricing, features, and basic "how-to"s a lot more accessible and useful pay dividends? Customers might be delighted, as well. I look for that trio. Said as a former sales engineer.
A few people can be deterred by a great FAQ and overall clear docs. But those are called "smart people." Others are either too dumb or just don't want to be bothered to spend any time looking for their answer, even in the most obvious places, before asking someone.