The Content Machine: Alex Lieberman's Anti-Slop Content Workflow

X postAlex LiebermanOpinion

Alex Lieberman details the architecture of the Content Machine, a 10-step content generation pipeline used at Tenex Labs. The system aims to eliminate generic AI output by forcing real personal input and structured automated interviews before any drafting begins.

Key points

  1. Two-layer structure: The generic pipeline and formatting specs reside in Git, while personal profiles, voice guides, and local databases remain strictly on the user's machine.
  2. The Oracle and Research agents: The system scans internal communication (Slack, Notion, Gmail, Linear, Git) and curated web feeds for spikes, building research briefs prior to writing.
  3. Interview Panel: Simulated interviewer personas question the author one prompt at a time, rejecting vague replies until two to three specific anecdotes are secured.
  4. Writer's Council and Revision Loop: Drafts are reviewed by six distinct personas targeting clarity, hook strength, and AI patterns; missing context is routed back to the creator rather than invented.
  5. Repurposing and Learning Loop: A single approved anchor piece fans out into 10+ platform-native derivatives, while diffs between first and final drafts continuously update personal style rules.

Why it matters

Most generative workflows suffer from bland, generic output when prompted without genuine personal data. Lieberman's framework constrains automation to research, extraction, and platform adaptation, reserving human effort exclusively for original input and final approval.

Analysis

Lieberman targets the extraction bottleneck rather than drafting speed. By enforcing an interview step and routing information gaps back to the author instead of allowing the LLM to invent context, the pipeline prevents common AI failure modes. The strict separation of local creator profiles from shared Git logic also provides a clean architecture for multi-creator environments.

Original post

Alex Lieberman

@businessbarista · 28 July 2026

Introducing the Content Machine! This was the first time I walked through the mechanics of our anti-slop content system & how we drive 10,000,000+ impressions at @tenex_labs with a marketing team of...2. Thanks to @clairevo for having me on her show to share. Full-writeup & t.co/HhhRVMrJJ5

847 likes122 replies2.4k bookmarks115.3k views

View on X
Selected replies (3)
  • @antoniowrites @businessbarista @tenex_labs @clairevo 🚀 insightful, would love to see this open sourced. Nice hook.
  • @sindhubiswal @businessbarista @tenex_labs @clairevo The interview panel is the real unlock here. Most content systems gum up at extraction, not drafting, you can't fake specificity, so forcing two or three concrete stories before it writes a word is the whole game.
  • @Alex_Gunnerson @businessbarista @tenex_labs @clairevo I've built out a personalized version of this I found myself falling into the same trap, publishing the thing that sounds good / would get clicks instead of whats actually true in my experience this system called me out on it. what a great experience.

Mentioned links

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Video

    Video:CURT

    Nicolas Cole: Content Strategy and Defensibility in the AI Era

    In an interview on the CURT YouTube channel, non-fiction writer and founder Nicolas Cole breaks down how generative AI changes the economics of online writing and software. He argues that both generic SaaS tools and commodity writing lack defensible moats. Instead, true leverage comes from having a distinct point of view (POV) and personal narratives. Cole outlines a three-tier content framework and explains how to train AI on personal approved language rather than generating generic AI slop.

    AI & LLMs· Discussion

  • X post:Meng To

    no-ai-slop: Skill removes repetitive AI writing patterns

    Meng To shares a workflow to counter generic AI writing, highlighting Peter Yang's open-source repository 'no-ai-slop', which strips more than 20 repetitive LLM clichés and robotic phrases from text.

    1.8kbookmarks126.6kviews

    AI & LLMs· Tool

  • Link:Sascha Hoffmann

    The Autopilot: Weekly Guide to AI Agents and Systems

    “The Autopilot” is a newsletter and publication by Sascha Hoffmann dedicated to building practical AI systems and agent workflows rather than relying solely on manual prompting, with an emphasis on content production, SEO, and growth.

    AI & LLMs· Resource

  • X post:Ren

    no-ai-slop: Tool to Remove AI-Generated Writing Habits

    An X post highlights the open-source project no-ai-slop, designed to strip characteristic AI writing patterns from articles. The repository gathered more than 7,700 GitHub stars within two months.

    777bookmarks33.6kviews

    AI & LLMs· Tool

  • Article:Peter Yang

    Open-Source Skill to Strip AI Slop and the 25/50/25 Rule for Writing

    Peter Yang has open-sourced an AI skill called /no-ai-slop for harnesses like Claude Code and Codex. The tool detects and removes over 20 repetitive patterns commonly produced by generative models. Alongside the release, Yang outlines a 25/50/25 writing process to retain editorial control.

    AI & LLMs· Tool

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.