Slice and Dice – analyze and explore User Prompts at scale
Hi HN, we’ve recently sold our previous product and are currently building on new ideas. This one may be the most exciting and overlooked growth opportunity for AI products we’ve found: TLDR: We’ve built a tool for analyzing and exploring user prompts — so you can actually understand how users are interacting with your AI product, and compare behavior across different segments (languages, paid vs free, etc). If you’re used to Mixpanel / Amplitude / PostHog to analyze user behavior, you could notice how irrelevant they become when your product is just a chat box (or voice…
In plain words
Slice and Dice is an analytics tool designed for AI product teams to analyze and explore user prompts at scale. It enables companies to understand how users interact with their AI products and segment behavior across different groups like language and subscription status. The tool uses natural language processing to cluster and explore chat data, addressing a gap in traditional analytics platforms like Mixpanel that focus on button events rather than text-based interactions in conversational AI applications.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hi HN, we’ve recently sold our previous product and are currently building on new ideas. This one may be the most exciting and overlooked growth opportunity for AI products we’ve found: TLDR: We’ve built a tool for analyzing and exploring user prompts — so you can actually understand how users are interacting with your AI product, and compare behavior across different segments (languages, paid vs free, etc). If you’re used to Mixpanel / Amplitude / PostHog to analyze user behavior, you could notice how irrelevant they become when your product is just a chat box (or voice interface). That's because in the age of AI you don’t need button events — you need to analyze a large corpus of text. To solve this, we’ve built what we call a Mixpanel for GenAI apps — an NLP tool to analyze and explore your user chats at scale. We can already do: 1/ Multi-layer semantic clustering (see a big picture of all the topics and drill down) 2/ Filters and groups (compare usage between languages, demography, free/paid, etc) 3/ Latent space exploration 4/ Semantic search of prompts 5/ Topics and token usage breakdown 6/ (coming) Trends and audience drift over time So you can answer questions such as: - What’s the main use case of my app? - What do users who pay the most do? - What do users who spend the most time do? - Which quiet audiences and use cases am I missing? - How do the user patterns differ between languages? - What are the new audiences we can appeal to? Please check the link for the screenshots and instructions on how to start! Any feedback is appreciated (I don't say I won't cry if it's negative)
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 · 26d ago · cactuscompute.com
Launched alongside, July 2025
the whole month →
Trickle - Magic Canvas ▲1,064The 1st Agentic Canvas for building apps visually with AI
AI · 2025 · trickle.so
- TB
Life & fun · 2025 · trytender.app
- TY
Today marks ten years, 3653 consecutive days, of running at least one mile every day under the USRSA rules [1]. To celebrate, I built an interactive dashboard that turns a decade of GPX files into charts you can explore. Running has truly changed my life: I've made lifelong friends, explored beautiful places, and more importantly invested into my own health and fitness, which I'm starting to see the positive benefits as I get older. The stack is pretty simple: a NextJS app, with a Postgres database to keep all my running data, and all the stats are pre-computed and cached in Redis, so I…
Dev tools · 2025 · nodaysoff.run
- DA
Made this website as an exercise in vibe-coding and GCP. It was posted about a few times around the internet, on sites like Morning Brew (https://www.morningbrew.com/issues/business-buzzkill), MetaFilter (https://www.metafilter.com/209703/Draw-A-Fish), boingboing.net, etc. I think it's cute! I built a basic CNN trained against penises and swastikas, and then anything that doesn't hit the 63% confidence score gets sent to a mod queue, a vibe-coded fish-tinder…
Dev tools · 2025 · drawafish.com
