Skip to main content
How I AI

How the founder of Morning Brew built a Claude content machine that never runs out of ideas and never sounds like slop | Alex Lieberman

42 min episode · 2 min read
·
Alex Lieberman

Episode

42 min

Read time

2 min

Topics

Career Growth, Remote Work, Investing

AI-Generated Summary

Key Takeaways

  • The Oracle System: Build an AI agent that scans all internal systems — Slack, Notion, Gmail, Linear, meeting notes — plus curated external accounts daily, scoring ideas on three criteria: presence of anecdote, strength of point of view, and specificity of examples. This produces 15 ranked content spikes per day, split evenly between internal and external sources, eliminating blank-page paralysis entirely.
  • Workflow Mapping Before AI: Before deploying any AI, map the full content process as it would run with zero constraints — not as it currently runs. Most teams discover non-AI inefficiencies first. Then assign each step as human-led, AI-copilot, or fully automated. This constraint-free design approach applies to any business process, not just content creation.
  • Voice Codification File: Train the AI on your top-performing posts by building a markdown voice guide that captures hook formulas, sentence structures, self-deprecating tone patterns, and latent content DNA. Pair this with a content lessons file that logs every piece of feedback given after drafts, creating a reinforcing loop that prevents the model from repeating the same errors across future drafts.
  • Interview Panel Over Drafting: Replace AI drafting with an AI interview panel modeled on six specific interviewers — Tim Ferriss, Joe Rogan, Larry King, Barbara Walters, Howard Stern, Michael Barbaro — trained to extract specific stories and customer examples. Use voice-to-text to answer. The resulting transcript becomes the sole source material; the AI only shapes structure, never invents content, which eliminates generic output.
  • Employee Creator Cup: Run a month-long internal content challenge with a points system — 10 points per post, 3 points per engagement with a colleague's post, 50 points for editor's pick — plus collective unlock prizes requiring 70% team participation. At 10x, this $5,000 investment targets engineering recruitment, where one hire from the campaign exceeds typical recruiting agency fees many times over.

What It Covers

Morning Brew founder Alex Lieberman demonstrates his Claude-powered content machine at his AI company 10x, walking through a five-step system — Oracle, research, interview panel, voice drafting, and writer's council — that generates non-generic LinkedIn and X posts by extracting the creator's own words rather than inventing AI-generated text.

Key Questions Answered

  • The Oracle System: Build an AI agent that scans all internal systems — Slack, Notion, Gmail, Linear, meeting notes — plus curated external accounts daily, scoring ideas on three criteria: presence of anecdote, strength of point of view, and specificity of examples. This produces 15 ranked content spikes per day, split evenly between internal and external sources, eliminating blank-page paralysis entirely.
  • Workflow Mapping Before AI: Before deploying any AI, map the full content process as it would run with zero constraints — not as it currently runs. Most teams discover non-AI inefficiencies first. Then assign each step as human-led, AI-copilot, or fully automated. This constraint-free design approach applies to any business process, not just content creation.
  • Voice Codification File: Train the AI on your top-performing posts by building a markdown voice guide that captures hook formulas, sentence structures, self-deprecating tone patterns, and latent content DNA. Pair this with a content lessons file that logs every piece of feedback given after drafts, creating a reinforcing loop that prevents the model from repeating the same errors across future drafts.
  • Interview Panel Over Drafting: Replace AI drafting with an AI interview panel modeled on six specific interviewers — Tim Ferriss, Joe Rogan, Larry King, Barbara Walters, Howard Stern, Michael Barbaro — trained to extract specific stories and customer examples. Use voice-to-text to answer. The resulting transcript becomes the sole source material; the AI only shapes structure, never invents content, which eliminates generic output.
  • Employee Creator Cup: Run a month-long internal content challenge with a points system — 10 points per post, 3 points per engagement with a colleague's post, 50 points for editor's pick — plus collective unlock prizes requiring 70% team participation. At 10x, this $5,000 investment targets engineering recruitment, where one hire from the campaign exceeds typical recruiting agency fees many times over.

Notable Moment

Lieberman reframes the AI slop problem entirely: when the content machine produces generic output, it reflects the creator failing to share specific stories and examples during the interview step, not a model failure. The AI can only shape what the human provides — weak input produces weak output.

Know someone who'd find this useful?

You just read a 3-minute summary of a 39-minute episode.

Get How I AI summarized like this every Monday — plus up to 2 more podcasts, free.

Pick Your Podcasts — Free

Keep Reading

More from How I AI

We summarize every new episode. Want them in your inbox?

Similar Episodes

Related episodes from other podcasts

Explore Related Topics

This podcast is featured in Best AI Podcasts (2026) — ranked and reviewed with AI summaries.

Read this week's Investing & Markets Podcast Insights — cross-podcast analysis updated weekly.

You're clearly into How I AI.

Every Monday, we deliver AI summaries of the latest episodes from How I AI and 192+ other podcasts. Free for one show.

Start My Monday Digest

No credit card · Unsubscribe anytime