Quickfire: Open source AMS for Insurance
A fast, open agency management system for P&C workflows
What it does
Quickfire is bleeding-edge, modern Agency Management System built for next-gen commercial P&C brokers who actually live inside their software all day. It’s not a reskin of legacy AMS platforms, and it’s not AI theater. Quickfire was built by a broker who has spent decades dealing with renewals, endorsements, audits, submissions, deadlines, and the constant pressure of things needing to just work.
Does a similar job
all alternatives →
- WBWe Built and Open Sourced a Feature Flagging Platform2018 · ▲11
Hi. We just open sourced Bullet Train, a Feature Flag and Remote Config platform. It's a collection of tools: server API, admin front end and clients for a bunch of different platforms. Together they allow you to control feature flags and remote config across projects, environments and users. We realised that we were building ad-hoc feature flag stuff into individual projects over and over, so we had a look around to see if there was a way of doing this in a more formal manner. There are a few commercial solutions around but they were quite expensive and seemed to be aimed more at the…
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 · 18d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 19d 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
