hello HN, let me tell you why i built boilerroom (https://boilerroom.ai).throughout my past endeavours in sales, the one thing that thoroughly pissed me off was living in a million places to execute one thing; the outbound motionthis includes everything top of funnel like finding leads (be it inbound or outbound), researching, filtering for qualification criteria, throwing them in a sequence, engaging them via dialer, email, and linkedin, gathering context, all the way through bottom of funnel like discovery calls, demo calls, and post-sales activitieswhat absolutely does not exist (or if it does, a piss-poor model) is a place to simply execute this work in one placewhy tf do i have to be on clay, or apollo, clicking around looking for leads, researching them around myself, put them in to some other garbage software to sequence to tell me when to make a call or send out automated emails, only to get a massive backlog of things I was supposed to do, which in turn makes my whole flow look like one big giant mess, which stresses me tf out, which reduces the shit out of my active revenue generating activities?One platform to solve allboilerroom is the only sales engagement platform for outbound teams, and the ONLY AI part is to handle the busywork around prospecting and calls, such as research, putting together context, transcribing calls, summarizing outcomes, and drafting the follow-up task before the rep has even gotten off the call. Otherwise everything else is pretty straightforward. Here’s what’s under the hoodunder the hood: - next.js 14 (app router) + react 19, prisma over postgres on supabase, deployed on vercel- calling runs through twilio on the server, the twilio voice js sdk for the in-browser webrtc dialer - call recordings get transcribed via elevenlabs - email sends through resend, plus gmail api oauth so reps can send from their own inbox instead of a shared one - meeting recording/transcription runs on top of recall.ai (their bot joins the call itself)for the actual ai part: call summaries, drafted follow-ups, account research briefs, and the scoring on our AI cold-call trainer — everything goes through a single OpenAI-compatible client pointed at Grok (api.x.ai/v1, grok-3-mini-fast)we started on anthropic s api for all of this and moved almost everything over to grok recently. calling an llm on every transcript/summary/draft shit adds up fastanyhow, if you run a sales team i d love your input/feedback/questions/ideas, especially from anyone who has opinions about what s missing or what we got wrong. happy to answer anything about the product or the stackcheers all