Morning Brew founder reveals Claude-powered content machine that generates 15 ideas daily

Morning Brew founder reveals Claude-powered content machine that generates 15 ideas daily

Yesterday
Lenny's Newsletter ARMARM Gtm_strategy

The Gist

  • Alex Lieberman's AI system scans Slack, Notion, Gmail for 15 ranked content ideas daily
  • Voice guide in Markdown captures his writing style, hook formulas, and content structures
  • AI Writer's Council refines drafts before publishing, eliminating blank page paralysis
Key Quotes

The blank page is the real enemy of consistent content, and an AI Oracle makes it disappear.

AI slop is mostly a people problem, not a model problem. The model is shaping clay, not inventing ideas. If the clay is bad, the sculpture will be bad.

Key Insights
  • An AI Oracle scans seven days of Slack, Notion, Gmail, and meeting notes, then surfaces 15 ranked content spikes each day—half from internal sources, half from the X and LinkedIn accounts he follows.
  • AI slop is mostly a people problem, not a model problem. The only time the Content Machine produces slop is when the person being interviewed doesn’t share interesting enough ideas during the interview.
  • Your voice lives in a Markdown file, and that file changes everything. The Content Machine pulls from a personal voice guide that captures top-performing posts, hook formulas, content structures, and specific language patterns.
  • A reinforcement loop is how your AI system gets better every time you use it. The system compares the original draft to the published version, extracts generalizable lessons, and asks if they should be added to a permanent lessons file.
  • The interview panel is the step most people skip and the one that matters most. The system deploys six interviewer personas that ask follow-up questions until they’ve extracted enough specifics to write something real.
  • Your employees are your most underleveraged marketing channel, and most companies are actively suppressing them. Alex ran a version of employee content at Storyarb called 'Own the Internet,' and it drove 40% of all inbound leads that quarter.
Actionable Takeaways
  • Map your current content creation workflow before implementing AI tools to identify inefficiencies.
  • Create a personal voice guide in a Markdown file to ensure AI-generated content aligns with your unique style.
  • Implement a reinforcement loop where the AI system learns from published content to improve future drafts.
  • Leverage employee advocacy programs to drive inbound leads and build personal brands for your team.
Data Points
  • 15 (ranked content spikes surfaced daily by the AI Oracle)
  • 40% (of all inbound leads driven by employee content at Storyarb)
  • $5,000 (prize pool for the Creator Cup at Tenex)
  • 9 out of 10 (minimum score required by the Writer’s Council for a draft to be published)

RevBots.ai View:

This ARM-stage content engine proves AI can systematize thought leadership at scale when built around core human insights.