Voicepanel – Gather Feedback Using AI
Hey HN, I’m Asa, one of the co-founders of Voicepanel (https://voicepanel.co). We’re building a new way to gather feedback using AI, as an alternative to running surveys. Simply share what you want feedback on; Voicepanel will recruit respondents, conduct open-ended interviews, and synthesize the insights automatically. Check out a demo here: https://youtu.be/6_C8netV38E, sign up for a free 7 day trial (https://voicepanel.co/) or try out examples of our product in action without a login (https://www.voicepanel.co/#examples). Why…
What it does
In the maker’s words, at launch
Hey HN, I’m Asa, one of the co-founders of Voicepanel (https://voicepanel.co). We’re building a new way to gather feedback using AI, as an alternative to running surveys. Simply share what you want feedback on; Voicepanel will recruit respondents, conduct open-ended interviews, and synthesize the insights automatically. Check out a demo here: https://youtu.be/6_C8netV38E, sign up for a free 7 day trial (https://voicepanel.co/) or try out examples of our product in action without a login (https://www.voicepanel.co/#examples). Why Voicepanel? When working at Google, my co-founder John was tasked with gathering fresh information from millions of local businesses. His team tried several approaches to this problem over the years, but found that the most effective method by far was to use an automated voice bot (powered by the Google Assistant) that would call businesses and ask basic questions like: “Are you open this Sunday?” With the recent advancement of LLMs and voice synthesis, John and I realized that this insight could be applied to the problem of gathering feedback. John and I both worked at Optimizely where we saw the benefits of combining quantitative data from things like A/B tests & surveys with qualitative data like user interviews. However, we never felt like there were good tools at the intersection of these two worlds. When looking at the options for gathering feedback or doing market research, some common methods are to either: (1) setup a survey or (2) conduct interviews. However, both methods have some drawbacks. Surveys are most useful when you can easily categorize the answer space in a way that’s useful and want to quantify the results (ex: “Which do you prefer?”). They are also easy to send out to a lot of people at once. Surveys don’t do as well when too many responses land in the “Other” category or you are seeking open-ended qualitative responses to not only explore a new answer space but also get at the underlying “why” behind a particular answer. Interviews on the other hand are perfect for open-ended questions (ex: “Interesting. Why do you feel that way?”), sharing designs and prototypes, and exploring the possible answer space. However, interviews don’t scale well. Scheduling interviews takes time, participants may not show up, conducting the interview in a consistent and unbiased manner takes lots of diligence and synthesizing the output can take weeks of manual effort to categorize and quantify the data. That’s why we are building Voicepanel. With the advent of LLMs and voice synthesis, we think this is a great time to introduce a new medium for gathering feedback that can combine the scalability and quantitative nature of a survey with the depth of a qualitative open-ended interview. We are excited to see what our users do with Voicepanel and look forward to everyone getting deeper, more insightful quantifiable feedback :)
Does the same job
all alternatives →
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, March 2024
the whole month →
- 3Y
Life & fun · 2024 · github.com
Microlaunch▲1,116Launch and get feedback on both the idea and product
Dev tools · 2024 · microlaunch.net
