TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Launch HN: ScopeAI (YC W17) – Extract insights from customer conversations

77 pointsby iloveluceover 7 years ago
I&#x27;m Luciano, co-founder and CTO of ScopeAI (<a href="https:&#x2F;&#x2F;www.getscopeai.com&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.getscopeai.com&#x2F;</a>). We’ve built a product that automates the process of extracting and communicating user insights to product and operation teams. To extract product insights, we integrate with support channels such as Zendesk, Intercom and desk.com and use NLP to automatically tag, categorize and cluster support tickets.<p>Customer support teams currently spend hours manually tagging customer support tickets to track trends in user feedback. The process is inefficient, lacks consistency and is reported retrospectively. This process typically fails to capture the granular insights requested by product and operation teams.<p>Natalie, our CEO is a former UX researcher. In that world, the process for extracting trends from user interviews was completely manual. It involved codifying the conversations and counting how frequently certain feedback was mentioned. It was definitely difficult to scale. We recognized that there needed to be a better way of extracting trends from unstructured data and started working on ScopeAI!<p>Some things we’ve learned&#x2F;be happy to discuss further:<p>-Our process for extracting key phrases from tickets - currently done through a custom pipeline built using spaCy<p>-How we connect similar phrases - currently using a word2vec model trained on both GloVe vectors and text from tickets in our system<p>-How we assign broader categories and sentiment analysis using Tensor Flow<p>Here&#x27;s an example of an insight we&#x27;d extract:<p>There were 67 requests for subscription cancellations for company x during the month of July:<p>• 24 requests “slow service”<p>• 19 requests “I have another account with y company”<p>• 8 requests “login issues”<p>Knowing this is really valuable for this company because they can make better decisions - in this case, making the software faster became a much higher priority.<p>Happy to answer questions and looking forward to hearing any feedback!

11 comments

Zee2over 7 years ago
Yelp, Google and other review aggregators do an interesting technique where they isolate significant phrases and intents from reviews and collect them into one report, and present it to the end user to help them make an educated decision. How does your technique compare? Are there significant differences in the objectives when catering to an internal audience (ticket management) instead of an external audience (public reviews)?
评论 #15287111 未加载
gargarplexover 7 years ago
As an operator of a subscription service, this sounds valuable. I would be interested in an app where I could connect my Drift account and get some data on this.<p>I would also be interested in a SaaS that simply managed cancellations and collecting feedback there.<p>Also, interested in a SaaS that does the same except for tracking true chain of referral (tracks down the customer and makes them answer &#x27;Where did you initially find us&#x27;, &#x27;What ultimately triggered the purchase&#x27;
boto3over 7 years ago
Sorry for the harsh words, but this looks like a solution looking for a problem. Any CEO of a company that&#x27;s lucky enough to have customers contacting them would spend a not trivial amount of their time reading and replying to the contacts. For example, Jan Koum, Whatsapp founder said that they only started hiring dedicated customer service staff when they reach 150M users [0].<p>[0] <a href="https:&#x2F;&#x2F;youtu.be&#x2F;8-pJa11YvCs?t=849" rel="nofollow">https:&#x2F;&#x2F;youtu.be&#x2F;8-pJa11YvCs?t=849</a>
评论 #15288242 未加载
评论 #15290006 未加载
评论 #15291262 未加载
评论 #15291568 未加载
arrmnover 7 years ago
This is an interesting topic, at my first job I&#x27;ve developed some tool to help our customer support, it&#x27;s a topic which is quite interesting for me.<p>On what data do you train your models? Do you train them individually for each customer with their own data, or do you take the data of all your customers and train &quot;universal&quot; model?<p>Another question about the broader categories, are they defined by you? I guess you&#x27;re doing some supervised learning. Is it possible for the customer to add own categories?
nedwinover 7 years ago
Awesome. Have recently started work on a well established product with a ton of data but it&#x27;s painful to go through all these channels manually and tag it all. Ideally we&#x27;ll get better at that over time but I know that we&#x27;ll miss out on some of those new tags, or adding verbatims to tags easily.<p>Requested access but 404 on your Calendly link to book a call...
评论 #15287208 未加载
whospabloover 7 years ago
Is there any integration for review channels on iOS&#x2F;Android app stores? Google play console currently has some tools around review analysis but I don&#x27;t believe the Apple app store does. This could be really helpful.
评论 #15287176 未加载
sebastianwover 7 years ago
Congrats on the launch Luciano and Natalie! The product sounds incredibly helpful and I&#x27;m eager to try it out.<p>I was wondering- if customer support tickets are coming into an inbox (like in gmail), can this also be integrated?<p>Thanks!
smith-kyleover 7 years ago
We were drowning in feedback at my old job, this would&#x27;ve been super useful. Can I customize the tags at all?
评论 #15289836 未加载
drc18over 7 years ago
Would this work with tickets where customers mix a bit of local language (spanish in our case) with English?
评论 #15290482 未加载
kuntajtsover 7 years ago
Whats the ideal number tickets coming through to get valuable feedback?
评论 #15287500 未加载
saycheeseover 7 years ago
What is your revenue model? Are there costs to use the platform? Etc.
评论 #15287350 未加载