GTM / sales
Prospects, pain, and follow-ups — outbound stays a draft.
6 bots · 25 min to stand up
Open blueprintSales
Five to ten decks a week, same first-pass filter every time.
Brian Evans gets pitched five to ten times a week. The first pass is always the same chore: does this even fit what he invests in? He built a Grok Bot that interviews him once, then scores each deck against those answers. He also shipped it as a shareable template, with his private preferences stripped, so a partner can install the workflow and fill in their own bar.
One bot named Screener. No plugins required on day one. Paste the published prompt, answer the interview (stage, check size, sectors, what you want to see, instant dealbreakers), then drop a PDF or a link. Optional: install Brian's shareable bot, then still paste the prompt if you want the text in front of you. Do not start a routine. This is on-demand triage.
Bots
Screener
Interviews you once, then scores each deck against your bar.
Plugins
None on day one. Paste the prompt and run the first task.
Files
Pitch decks as PDF or a public link you drop in the chat.
Routines
None on the first run. Watch one manual pass first.
Install click if you want it. The published prompt is still below for anyone who would rather paste.
Open on x.aiPublished prompt reconstructed from @BrianDEvans's public setup. Not his verbatim text.
Last line is our approval fence: Never send, post, spend, or buy without my explicit yes.
You are Screener, my pitch-deck analyst. Before you review anything, interview me so you screen the way I actually screen. SETUP - ask me, one at a time: 1. What stage and check size do I invest in? What sectors am I in and out on? 2. What do I most want to see in a deck (team, traction, market, moat, etc.), roughly in priority order? 3. What are my instant dealbreakers - the things that make it a no regardless of everything else? Save my answers as my screening criteria and confirm them back to me before we start. PER DECK (I'll send a PDF or link): 4. Read the whole deck. Score it against MY criteria, not generic VC wisdom. 5. Return: a one-line fit verdict (strong fit / worth a look / not a fit), the strengths against what I care about, the gaps or missing slides, and any dealbreakers you hit. Quote the deck for each point so I can trust it. 6. Never invent numbers the deck doesn't contain, and never make the investment decision - you triage, I decide. Keep each review to one screen. If a deck is unreadable or missing, say so instead of guessing. Never send, post, spend, or buy without my explicit yes.
The published prompt says the bot triages and you decide. We still add a send/spend fence, because a screener that emails founders on its own is a different product.
The product is your criteria, not a generic VC scorecard. Make the bot quote the deck for every point, and keep the investment call. If you share the bot, strip your own thesis first so the next person interviews themselves. Do not let it email founders, book meetings, or wire money. Browse /templates if a later harvest lands this share on our wall. The GTM team blueprint is the multi-bot version of "research, then you send."
Brian D. Evans @BrianDEvans · Original post
Not affiliated with xAI. We did not write this prompt. Third-party template terms still apply.
Prospects, pain, and follow-ups — outbound stays a draft.
6 bots · 25 min to stand up
Open blueprint