---
name: al-690-run-product-work-as-voice-note-grill-the-idea-linear-spec
description: "On Nov 3, 2026 Greg Isenberg posted a widely shared X thread (hundreds of thousands of views) about running a 50+ person, 12-country company by talking to agents more than teammates. The stack: voice note to Grok Bot; mattpocock/skills /grill-me to interrogate the idea; Linear MCP for the spec; Exa/Firecrawl research plus Apify review mining for top user complaints; four design options before code; parallel agents in git worktrees; headless persona testing on Vercel previews; Sentry MCP opening fix PRs in under 10 minutes; PostHog cron watching funnel drops. Operating rules: one agent per platform, cheap models for triage and Opus for shipped work, LLM judge scores under 8 get sent back, mistakes become reusable skills. Humans get version five, not the raw voice note. Use when the user wants help with founder multi-agent product loop from voice note to fix pr (business strategy) for a small business."
---

# Run product work as voice note → grill-the-idea → Linear spec → parallel agent build → persona browser QA → Sentry fix PRs, so humans only see version five

On Nov 3, 2026 Greg Isenberg posted a widely shared X thread (hundreds of thousands of views) about running a 50+ person, 12-country company by talking to agents more than teammates. The stack: voice note to Grok Bot; mattpocock/skills /grill-me to interrogate the idea; Linear MCP for the spec; Exa/Firecrawl research plus Apify review mining for top user complaints; four design options before code; parallel agents in git worktrees; headless persona testing on Vercel previews; Sentry MCP opening fix PRs in under 10 minutes; PostHog cron watching funnel drops. Operating rules: one agent per platform, cheap models for triage and Opus for shipped work, LLM judge scores under 8 get sent back, mistakes become reusable skills. Humans get version five, not the raw voice note.

## Inputs to collect first
Ask the user for anything below that they haven't already given you. Don't guess missing facts.

- My product
- Grok Bot / Claude / Cursor
- Exa/Firecrawl

## Instructions

Do the task below with the user's inputs in place of each [bracket].

Help me install a Greg-Isenberg-style agent product loop for [my product]. Stack I have or will use: [Grok Bot / Claude / Cursor], Linear, [Exa/Firecrawl], git worktrees, Vercel, Sentry, PostHog. Hard rules: agents never ship to production without my approve; no password in browser agents—I take over at login; one agent per platform; score every output 1–10 and redo under 8. 1) Map my workflow stages and which agent owns each. 2) Draft the /grill-me and research prompts (top 10 quoted complaints). 3) Spec overnight build + morning review checklist. 4) Define the Sentry→fix-PR and PostHog funnel-drop cron prompts. Output a one-page operating manual I can paste into each agent.

## Safety checks (share these with the user)

- Check names, dates, numbers and any claim against your own source material before you use the answer. AI can misread or invent details.
- Say clearly which parts need a person to review or approve before anything is sent, paid, posted or filed.

## About this skill

- Works with: Grok Bot, Claude/Opus, Linear MCP, Exa, Firecrawl, Apify, Vercel, Sentry MCP, PostHog MCP, Cursor
- Based on this real-world example: https://x.com/gregisenberg/status/2117734977312047537
- Free prompt from AgentPlaybook Real Estate: https://agentic-library.netlify.app/prompt/al-690-run-product-work-as-voice-note-grill-the-idea-linear-spec-pa/
- To install in an agent that supports Agent Skills, save this file as SKILL.md in a folder with the same name as `name` above (for example in your skills directory). Install steps for Claude.ai, Claude Code, Cursor and Codex: https://agentic-library.netlify.app/skills/