Asklet
AI-powered NPS widgets that collect natural voice feedback
189 followers
AI-powered NPS widgets that collect natural voice feedback
189 followers
Asklet widgets ask quick, finely-tuned questions that get better feedback from your customers and users. Let users respond by voice or text, and get the rich detail you need to identify issues faster and easier.
Asklet
Meteor
Very excited about this! I'm so tired of useless, stale surveys, both when I'm asked to fill one out and when reading the generic analysis that goes on top of the dataset. Voice is the new UI!
Asklet
@brendan_gill Absolutely. We went back-and-forth a few times thinking about how much better voice would be, but for short-form CX surveys I think it genuinely makes it much easier to get human detail.
Asklet
Having worked in the UX & Tech industry for many years, I know how valuable this could be!
Researchers know that user feedback should be as natural and authentic as possible, and given of their own volition. However there's nothing natural about what we do currently with feedback widgets—contriving all their nuanced and rich feedback into a simple score out of 10, or thumbs up.
My hope for Asklet is that it helps us bridge that gap between collecting feedback at scale and collecting much more nuanced, detailed, and human responses that can be genuinely useful in measuring success and making improvements to the customer experience.
Excited to see where it goes! ☺️ 🚀
Asklet
It's been so much fun building out Asklet over the past few weeks, I thought I'd share a little more detail on how it works and what's powering it.
Asklet has been built with the same tech we use across the rest of our Surveys platform - Elixir, Phoenix LiveView and Postgres. Why this stack? We've found it incredibly efficient to work with as a small team of 4, and it's built for robust realtime experiences which is exactly the feel we wanted people to have.
For infrastructure we're on Amazon's Elastic Container Service (ECS) which has many of the key elements of full Kubernetes, but with less maintenance overhead. It's a good balance between a fully fledged PaaS, and an entire DIY approach. All the benefits of multi-region scaling, with much less Yaml to wrangle! This is the right fit for us now, but because the application is containerised with few dependencies we can easily move to something else if it makes sense in the future.
The most complex piece was creating a solid experience for users who opted for voice usage. We felt it was important to make this as slick as possible, and allow movement between voice and text modalities for accessibility. After playing around with a few options we settled on a WebRTC connection to OpenAI's Realtime API - this is primarily designed for telephony like products so we spent most of our time tweaking the integration to get it just right for what we needed.
Some of the other challenges we dedicated time to were:
Finding the balance between digging deeper for the best possible feedback, and not creating a tedious or frustrating experience for people who were responding.
Supporting a preview experience for those building an Asklet, as well as a standalone and embeddable version for respondents.
At some point we'll put up a more detailed explanation of how it all works, but feel free to drop any questions. We're really happy to share!
Asklet
Such an important consideration I forgot to mention. It's made a huge impact on how well they work ✨
Fullview
Really awesome product with a lot of potential!!
Swytchcode
Congrats on the launch!
Asklet was a great tool to preview. I can see how it would help organizations stay more in touch with their customers through this. I can also see how it could be used as an internal tool as well. How quickly would it be to get feedback from an employee who is out on the field and doesn't sit at a desk to be able to answer a typical questionnaire? The dashboard seemed really helpful and easy to use.