Lenny Rachitsky · 4 min read · Gen AI Tools
🎙️ How I AI: How the founder of Morning Brew built a Claude content machine that never runs out of ideas
Read the original on lennysnewsletter.com →
Alex Lieberman describes a Claude-based content machine that continuously generates ideas, featuring an AI Oracle that surfaces daily content spikes, an interview-panel to extract compelling inputs, and a voice-guided drafting process. The system emphasizes mapping existing workflows, preserving a personal voice, and using feedback loops to improve content over time.
Key Takeaways
- Map your existing content workflow before adopting AI to reveal non-technical inefficiencies and set a realistic process.
- Use an AI Oracle that aggregates internal signals (Slack, Notion, Gmail, meetings) and external follows to surface about 15 ranked content spikes daily.
- Anchor the AI to a centralized Markdown voice guide so drafts reflect your actual style, language patterns, and hook formulas.
- Employ a six-person interviewer panel (with distinct personas) and voice-to-text capture to ensure authentic, specific content.
- Implement a reinforcement loop: compare drafts to published pieces, extract lessons, and continuously update a permanent lessons file to avoid repeating mistakes.
Excerpt
How the founder of Morning Brew built a Claude content machine that never runs out of ideas | Alex Lieberman (Tenex) Listen now on YouTube • Spotify • Apple Podcasts Brought to you by: Firecrawl —Power AI agents with clean web data Customer.io —Build customer engagement campaigns from a single prompt Claire sits down with Alex Lieberman, Co-founder and Co-Managing Partner of Tenex, to dig into the AI content system he’s built inside Claude. Alex walks through how he finds ideas, gets interviewed by AI, codifies his voice, and runs drafts through a “Writer’s Council” before posting. Biggest takeaways: The…