Human Behavior
Product analytics told you what happened. We handle it.
In plain words
Human Behavior is an AI-powered analytics platform that automatically detects and acts on user experience issues. It collects session replays, events, and errors through a single SDK, then uses AI to identify problems like rage clicks and abandoned interactions. Rather than relying on dashboards, the system automatically notifies affected customers, updates project management tools, and creates pull requests with evidence—all surfaced through Slack or SMS. It's designed for product teams who want to move beyond traditional analytics dashboards toward autonomous problem-solving.
written from the facts on this page · September 2026
From the sources
Dashboards are where insights go to die. Human Behavior closes the loop: 1) Collect. Our SDK captures your events, errors, and session replays. 2) Understand. AI watches every replay, catching rage clicks, dead buttons, and silent give-ups. 3) Act. Background agents email the customer, update Linear and your CRM, and open PRs with the replay as evidence. 4) Loop. Agents check the results and keep the product improving — on its own. No dashboard to babysit. It all lives in Slack or SMS.
An AI that watches every session, catches what your dashboards miss, and acts on it — opening PRs and reaching the users affected.
An AI that watches every session and acts on what your dashboards miss. An AI that watches every session, catches what your dashboards miss, and acts on it — opening PRs and reaching the users affected. Drop one SDK into your app to capture session replays, logs, traces, web analytics, and performance, at full parity with PostHog. Session replays, console logs, network traces, and web analytics stream in from a single snippet, with nothing else to wire up. Pageviews, conversions, and performance metrics are tracked alongside every session, so every number comes with full context. Build funnels and follow each user journey end to end, from the first pageview to the moment they convert or…from humanbehavior.co
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 · 16d 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, August 2026
the whole month →- TL
Life & fun · 9d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
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 · 16d ago · simedw.com