BreakRoom, draft messages/documents using the information in your files
Hi HN! BreakRoom is a tool that lets you upload files, then uses the information in them to draft messages, responses, and other types of documents. I felt like existing AI tools require careful prompting to get usable results, making them hard to use for less tech/AI savvy users. I built BreakRoom to let users get usable results with very little prompt engineering — it uses information from your repository of files when relevant, and has a pre-written set of chain-of-thought prompts for each use-case. Full transparency, I wanted to build a tool that did all this directly within a Gmail…
What it does
In the maker’s words, at launch
Hi HN! BreakRoom is a tool that lets you upload files, then uses the information in them to draft messages, responses, and other types of documents. I felt like existing AI tools require careful prompting to get usable results, making them hard to use for less tech/AI savvy users. I built BreakRoom to let users get usable results with very little prompt engineering — it uses information from your repository of files when relevant, and has a pre-written set of chain-of-thought prompts for each use-case. Full transparency, I wanted to build a tool that did all this directly within a Gmail inbox, but Google’s new security audit requirement for sensitive scopes was a barrier to entry. I figured I’d build something quick and dirty to validate usefulness and iterate first. I wanted people to have a little fun with it too so check out the "After Hours" toggle on the top right :) Thank you to anyone that uses BreakRoom and/or provides feedback. Thanks! Ashwin
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 · 26d ago · cactuscompute.com
Launched alongside, February 2024
the whole month →
MarketingIdeas.com▲1,230Never run out of marketing ideas ever again
Growth · 2024 · marketingideas.com
