Askmore – Let an AI run user interviews on your behalf
Hi HN, We're Arindam and Julien and we're building AskMore.ai. AskMore uses an AI to run user interviews on your behalf. We like to think about it as a new user research method that sits between traditional user interviews and user surveys: It's as easy as sending a survey link but the AI will adapt to the user answers, follow up and dig deeper to provide you with insights as deep as what you'd get in a user interview. We got the idea after a lot of struggles to get feedback on our other side projects. We couldn't get many user interviews (low response rate, long delays to schedule calls),…
In plain words
Askmore is an AI-powered user research tool that conducts interviews automatically on behalf of product makers. Users create a research prompt and share a link; the AI adapts its questions based on responses, follows up for clarification, and provides insights comparable to traditional interviews. It targets product developers and researchers seeking faster feedback than scheduling calls allows, while gathering deeper insights than standard surveys. The tool delivers results in days rather than weeks.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hi HN, We're Arindam and Julien and we're building AskMore.ai. AskMore uses an AI to run user interviews on your behalf. We like to think about it as a new user research method that sits between traditional user interviews and user surveys: It's as easy as sending a survey link but the AI will adapt to the user answers, follow up and dig deeper to provide you with insights as deep as what you'd get in a user interview. We got the idea after a lot of struggles to get feedback on our other side projects. We couldn't get many user interviews (low response rate, long delays to schedule calls), and surveys were providing answers that were too shallow. We have a few people running interviews on AskMore and the main benefits we're seeing are: - You can get feedback way faster than if you had to schedule calls (for instance we got more than 40 answers to our own interview in just a few days). - It works in any language so you can interview users you couldn't hear before. - It's more lightweight for the participant so you get a better response rate and it can even be a good first step that can unlock a call. - The AI follows user research best practices (we've been particularly inspired by The Mom Test, but you can override everything) so you don't need to know how to ask the right questions. In fact, I've been amazed multiple times by how the AI would adapt to the conversation and find insights I wouldn't have been able to find myself if I had been conducting the interview. Something important is that we don't think this should replace traditional interviews. It's still super important to connect directly with your users. But this could be a good complement to get more feedback, or to help making the first step. It's super early and rough, but it works and we're eager to get more feedback and to see how it behaves on more use cases. Feel free to give it a try (message us on our Intercom, we can provide more free credits) or just share your thoughts on the concept. Thanks!
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, August 2023
the whole month →
Lottielab▲871Create and ship lottie animations to sites and apps faster
Dev tools · 2023 · lottielab.com
- LC
Outlines is a Python library that focuses on text generation with large language models. Brandon and I are not LLM experts and started the project a few months ago because we wanted to understand better how the generation process works. Our original background is probabilistic, relational and symbolic programming. Recently we came up with a fast way to generate text that matches a regex (https://blog.normalcomputing.ai/posts/2023-07-27-regex-guide...). The basic idea is simple: regular expressions have an equivalent Deterministic-Finite Automaton (DFA) representation. We…
AI · 2023 · github.com