We scan new podcasts and send you the top 5 insights daily.
Katie Parrott is adding audience.md to Compound Writing, alongside voice and style guides. It captures the reader profile and hero's journey, then reviews drafts for audience fit and flags where the piece loses the less-expert reader. This makes the writing tool focus on who the draft is for, not just how it sounds.
Run content through a custom AI agent trained on your specific buyer persona. This tool can flag jargon or phrasing that is technically correct but misaligned with the target audience's language, ensuring your message lands effectively before it goes live.
Go beyond asking AI to just write content. Use it to refine your work. For example, feed a video script into a custom agent and ask it to identify where audience retention might drop, suggest secondary hooks, or increase tension to improve watch-through rates.
Writer Katie Parrott achieved massive output by first building foundational documents: style guides, audience personas, and product specifics. This "context engineering" creates guardrails for the AI, ensuring consistent, on-brand results and turning a manual process into a repeatable, high-speed system.
Go beyond basic ICPs. Create dynamic audience profiles for your AI that detail jobs-to-be-done, specific pain points, a 'vocabulary library' of words they use, and their 'emotional register' to ensure content resonates on a deeper level.
Standard ICPs with firmographics and demographics are insufficient for AI. An 'Audience Delight Profile' captures what emotionally resonates: their vocabulary, what makes them 'light up,' and what frustrates them. This provides the nuanced context AI needs to create content that truly connects with your audience.
To avoid AI content that assumes too much context, build a multi-agent system where a final "cold reader" agent reviews drafts. This agent mimics a real audience member by lacking prior knowledge, flagging confusing or unnatural phrasing.
Providing agents with isolated markdown files for audience analytics, creator perspective, and editorial taste prevents generic generation. Instead of relying on a single prompt, individual bots ingest specific context files to evaluate content ideas against engagement history and a creator's unique point of view.
To make AI-assisted writing more effective, first create detailed personas of your target readers. Then, have these AI personas review your drafts, providing specific feedback on clarity, impact, and what would make them disengage. This allows for unlimited, targeted feedback cycles.
Move beyond generic audience personas. To give your AI a precise understanding of your target reader, provide it with the actual LinkedIn or X profiles of five "dream readers." This grounds the AI's audience model in real people, leading to more relevant and targeted content.
Focusing on refining prompts (skills) yields diminishing returns. The breakthrough in AI content quality comes from building a 'foundational layer' of shared intelligence—core documents defining your audience, voice, and positioning—that every AI skill draws from, preventing it from starting from zero each time.