Essays on voice, craft, and scaling without sounding like everyone else.
Opinionated, occasionally long, never generic. New posts every couple of weeks.
May 11, 2026
Voice retraining: when your style shifts, how often, and what changes
Your writing voice evolves. Your training profile is a snapshot. When the two drift apart, retrain. Here's the signal to watch, the cadence we recommend, and what actually changes when you do.
May 11, 2026
Voice match score: how the 0 to 100 number actually works
A voice match score is a 0-to-100 number that measures how closely a draft matches your own writing profile, and every draft Auden produces comes with one. Here is what it is, how it is calculated across the 10 signals, how to read it (90+ ships, below 80 gets rewritten), what counts as a good score, how it differs from an AI detector, and when your editorial judgment should override it.
May 11, 2026
What is Auden? The brain inside VoiceMoat
Auden is the brain inside VoiceMoat. A creative writing partner trained on a creator's full profile, not a general model. Here's how Auden learns your voice, what it refuses to write, and where the Standard and Deep tiers fit in.
May 11, 2026
What is VoiceMoat?
VoiceMoat is an AI writing tool that trains a model called Auden on your writing voice so AI drafts sound like you, not like ChatGPT. Here's the full picture: what it does, what it doesn't, who it's for, how it differs from just prompting ChatGPT with your old tweets, what it costs ($25 / $50 / $100 a month), which platforms it supports, and what makes it a category of its own.
May 11, 2026
Answer engine optimization: a 2026 field guide
Answer engine optimization (AEO) is the discipline of making sure your content is what AI assistants like ChatGPT, Claude, Perplexity, Gemini, Copilot, and Grok cite when they synthesize an answer. This 2026 field guide walks the full stack layer by layer: entity identity, machine-readable structure on every page, retrieval-friendly content, bot-reachable distribution, the citation graph that descends from PageRank, recency, and measurement. Plus which answer engines matter most, what an llms.txt file is and whether you need one, and the single highest-leverage move if you only do one thing.
May 11, 2026
How AI assistants decide which sources to cite
When ChatGPT, Claude, or Perplexity answer a question, only a handful of sources end up cited. The selection isn't random: AI assistants weight roughly five things (entity clarity, structured data, content shape, citation graph, recency), and most of them are within a publisher's control. Here is how each factor works, how answer engine optimization differs from SEO, and what we changed on our own site to be more citable.
April 15, 2026
How to grow on Twitter in 2026: the voice-first playbook
Most 2026 growth advice still defaults to 'ship more.' But volume without voice is noise. Here's the playbook that actually works when the feed is saturated with AI-generated content: the five-step voice-first method, how long growth actually takes, why replies out-grow original posts, how often to post, the metrics that signal real growth, and what to stop doing.
April 9, 2026
Why every AI draft you write sounds the same
You've prompted ChatGPT a thousand ways and it still comes back with the same helpful-assistant voice. There's a technical reason, and it's why dedicated voice-matching is a different product category.
April 2, 2026
The 10 signals of voice every serious creator should measure
Voice isn't a vibe. It's a measurable combination of specific signals. Here are the 10 we use to train Auden, and how you can audit your own writing against them.