I built an LLM powered receptionist for website chats
I built Receptionst after noticing a pattern across my own projects. Visitors would open the website chat widget, ask a question and leave before I could answer. If it happened during deep work I missed it. If it happened overnight I never saw it at all. It became obvious that I could not respond instantly which meant I was losing leads without realizing it. I wanted something lightweight that acted like a receptionist by giving instant LLM powered answers based on my own content and by collecting lead details when visitors showed intent. I kept the scope narrow so setup is simple. You…
In plain words
Receptionst is an AI-powered chat widget for websites that provides instant answers to visitor questions based on a site's own content. It collects visitor details when they show purchase intent, helping website owners capture leads they might otherwise miss during offline hours or periods of unavailability. The tool requires minimal setup—users connect their website, add relevant information like docs and FAQs, and the LLM begins responding to inquiries with contextual knowledge from those sources.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
I built Receptionst after noticing a pattern across my own projects. Visitors would open the website chat widget, ask a question and leave before I could answer. If it happened during deep work I missed it. If it happened overnight I never saw it at all. It became obvious that I could not respond instantly which meant I was losing leads without realizing it. I wanted something lightweight that acted like a receptionist by giving instant LLM powered answers based on my own content and by collecting lead details when visitors showed intent. I kept the scope narrow so setup is simple. You connect your site, add the info you want it to know and it starts responding with context from your docs, pricing pages and FAQs. I am happy to answer questions about the tech choices, the prompting, or the things I would do differently.
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, November 2025
the whole month →
- IB
Life & fun · Nov 2025 · bitsnpieces.dev
- BBoing▲782
Life & fun · Nov 2025 · boing.greg.technology