More How I AI episodes

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

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

Published 20 Jul 2026

Duration: 00:42:58

"AI-driven content creation balances efficiency and quality through structured workflows, human oversight, and scalable systems like the 'content machine,' optimizing idea generation, research, and drafting while ensuring authenticity."

Episode Description

Alex Lieberman co-founded Morning Brew in college and grew it into one of the most-read business newsletters in the world before selling it to Busines...

Overview

The podcast discusses a systematic, AI-assisted approach to content creation called the "Content Machine," designed to maximize efficiency for individuals and teams with limited time. This framework begins with an "Oracle" that scans internal and external sources to generate 15 ranked content ideas daily, followed by AI-driven research, interview simulations, and drafting in the user's authentic voice using personalized style and voice guides. The process emphasizes overcoming creative friction - such as the "blank page" problem - by leveraging AI to generate ideas, refine drafts through a simulated "Writer's Council" of expert personas, and maintain consistency through feedback loops and a centralized vault of content ideas.

AI is positioned not as a replacement for human creativity but as a tool that amplifies it, particularly when integrated into well-mapped workflows. The system enables employees to become content creators without leaving their primary roles, promoting employee advocacy as a powerful distribution strategy. Examples include internal challenges like the "10X Creator Cup" to incentivize social sharing and past successes where employee-generated content significantly boosted leads and hiring. The podcast also explores broader applications of AI in business transformation, emphasizing that successful integration requires rethinking workflows without constraints, combining subject-matter expertise with AI capabilities, and using reinforcement loops to continuously improve output quality.

What If

  • What if you could offload your content idea burnout by automating daily high-potential prompts based on real business activity?

    • Move: Set up a simple "Oracle" script that scans your last 7 days of Slack messages, email threads, and meeting transcripts (via Whisper) to extract 3-5 ranked content ideas daily using an LLM. Store in a Notion database.
    • Why Now?: You're wasting prime creative time brainstorming instead of executing - especially critical when you only have 10 - 20 hours/week for marketing. The tools (LLMs, transcription, automation) are now plug-and-play.
    • Expected Upside: Cut idea-generation time by 70% and increase output frequency from 1 - 2 posts/month to 2 - 3 high-relevance pieces/week, directly tied to actual projects or customer interactions.
  • What if you turned your next customer call into 5 pieces of content in under 30 minutes - without writing a word?

    • Move: After each sales or discovery call, feed the transcript into an AI workflow that: (1) extracts key insights, (2) simulates a Tim Ferriss-style interview to expand them, (3) drafts a LinkedIn post and email snippet in your voice using a stored style guide.
    • Why Now?: Recorded calls are already piling up in your CRM or Zoom library - untapped, high-signal material. AI transcription and repurposing are now fast, cheap, and accurate enough to exploit this gap immediately.
    • Expected Upside: Turn one 30-minute conversation into a week's worth of trusted, authentic content that builds distribution - while freeing you to focus on product, not posting.
  • What if you built a personal "Writer's Council" of AI editors to grade every draft before publishing - forcing quality without slowing output?

    • Move: Create 3 - 6 AI personas (e.g., "David Perell," "Blunt Marketing Mentor") that each score your draft 1 - 10 and give line edits. Only publish if 3 score it 9+. Use failed drafts to extract "content lessons" you feed back into the system.
    • Why Now?: Solo creators often publish subpar content due to blind spots. With AI, you can simulate consistent, critical feedback loops instantly and iteratively raise your baseline quality.
    • Expected Upside: Reduce weak posts from ~40% to under 10%, while building a growing repository of personalized content rules that compound quality over time - making your voice sharper and your audience more loyal.

Takeaway

  • Implement a daily idea-generation system that scans internal (e.g., Slack, email) and external (e.g., news, social) sources to surface 5 - 15 ranked content ideas based on relevance, story potential, and personal voice fit.
  • Build or adopt a structured content workflow that includes a research brief step before drafting, ensuring each piece is grounded in insights or debate, even when repurposing from meetings or transcripts.
  • Create a personal voice and style guide using your top 5 performing posts, then integrate it into AI tools to maintain authentic tone and increase approval rates of AI-assisted drafts.
  • Set up a feedback loop where every edited piece contributes one approved lesson (e.g., "improved hook" or "clarified argument") to a growing markdown file used to refine future AI-generated content.
  • Launch a personal content repurposing system: after publishing one core piece (e.g., LinkedIn post or newsletter), automatically generate 3 - 5 micro-versions (e.g., tweets, bullets, quotes) tailored to different platforms using AI and your style guide.

Recent Episodes of How I AI

6 Jul 2026 How I run autonomous coding agents from my phone with OpenAI Symphony + Linear | Alessio Fanelli (Kernel Labs)

AI automates small business tasks like inventory tracking and order management via tools such as "magic glasses," explores personal AI use cases (e.g., Codex for hobby tasks), delves into autonomous agent orchestration with cloud-based workflows and GitHub, addresses challenges like scalability and model behavior, and reflects on AIs potential to bridge physical-digital systems, reduce manual effort, and enhance productivity while highlighting underutilized automation opportunities.

30 Jun 2026 Sonnet 5 review: I ran 64 generations to find out if it's worth it

Anthropic's Claude Sonnet 5 offers Opus-level performance at reduced costs with enhanced agentic capabilities, while a new benchmarking framework evaluates its competitive edge against models like Gemini 3 Pro and GPT 5.5, highlighting the need for standardized, human-informed evaluations to balance objective metrics and subjective quality.

More How I AI episodes