What are the key takeaways from this How I AI episode?

Key insights include: **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.

What did Alex Lieberman discuss on How I AI?

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 topics include: **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..

How long is this episode of How I AI?

This episode is 42 minutes long. SignalCast provides an AI-generated summary so you can get the key insights in about 3 minutes.

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

July 20, 2026

42 min episode · 2 min read

Alex Lieberman

Episode

42 min

Read time

2 min

Topics

Career Growth, Remote Work, Investing

AI-Generated Summary

Published Jul 20, 2026

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?

Episode Transcript

Creating content has afforded me so many opportunities, but I am capped on the amount of time that I can spend creating content every day. And so I've been basically thinking about how can I reengineer my content process to be AI native or AI assisted? The other problem I've been trying to solve is how do I make it as easy as humanly possible for employees to be creators while they have full time jobs? And so that was kind of the genesis of this content machine idea was optimizing for these two problems. I do read your posts. They're quite good. So they don't strike me as slop, but prove it live. How would we go through this process? So the first step of the content machine is called the Oracle. The Oracle just does a scan of the last seven days of information from all of the channels that I'm in, and it ranks a short list of ideas. And it has, like, a whole scoring system for what it defines as a good content spike. It gives it a positive score. I basically get 15 content spikes. AI is just out of the box, pretty terrible at writing. How you get it to not write slop? The only time in my view that the content machine actually produces slop is more of an indictment of the person not sharing good enough ideas during the interview step than the AI writing bad stuff. Uh-oh. So what you're saying is we are actually the slop. My take is that AI slop is hilariously people just pointing the finger at themselves and saying, I'm not intelligent enough. Welcome to How I AI. I'm Claire Vaux, product leader and AI obsessive here on a mission to help you build better with these new tools. Today, I have Alex Lieberman at ten x, and he's gonna show us how he climbs Cringe Mountain, aka builds a content machine at his company by using AI, and guess what? He doesn't get AI Slop out. This is an awesome workflow for anybody trying to market their company and get an edge on distribution. Let's get to it. Quick word from today's sponsor, Fire Crawl. If you're building with AI agents, you've probably hit the same wall. Your agent needs data from the web, but the right pages are difficult to find, buried in JavaScript, or blocked behind logins. Fire Crawl is a web data API that lets agents search, scrape, and interact with the web at scale and get that clean, structured data they can actually use. Over a million developers, including myself, build on it. It's open source, and it's free to start. Stop fighting the web for data and start powering your AI agents and apps with Firecrawl at firecrawl.dev. Use code how I a I to get 10,000 free credits today. Alex, I am excited about this episode because I tell everybody, in order to make it, certainly as a …

Get the full transcript (8,374 words) + summary by email — free

One-time email with the complete transcript and AI summary of this episode. No account needed.

One email, no spam. We’ll also show you what SignalCast does.

Browse all How I AI transcripts →