Get your free personalized podcast brief

We scan new podcasts and send you the top 5 insights daily.

While writing his book, Roose used several specialized AI personas—including an industry booster, a skeptic, and a biographer—to critique drafts. This council caught factual oversights and weak arguments without compromising authorial voice or delegating actual prose generation.

Related Insights

By assigning roles like a contrarian, an expansionist, and a first-principles thinker to a single LLM, founders can get multi-faceted feedback on critical questions. The model debates itself and provides a synthesized recommendation, revealing blind spots that a single-prompt approach would miss.

Create a complex AI persona that acts as a personal "board of directors." Include real-world experts (e.g., Ben Thompson for strategy) and archetypes (a skeptic, an investor). Run your ideas and documents through this virtual board for multi-faceted, high-quality feedback before finalizing.

Use Claude Cowork to spin up multiple "sub-agents" with distinct personas (e.g., your boss, customer, skeptic). These agents review your work from different perspectives, providing objective, multi-faceted feedback before you present it to real stakeholders.

To get robust feedback, create an AI tool that simulates a "war council." It spins up multiple AI sub-agents, each with a specific persona like "Ruthless CFO" or "Contrarian Board Member," to debate a critical decision from all angles.

For complex strategic decisions, create multiple AI personas representing different mentors or archetypes. Instruct this AI "board" to debate the issue among themselves before presenting you with a summary of their diverse viewpoints, avoiding the bias of a single AI voice.

Instead of asking for generic feedback, sophisticated writers prompt LLMs to adopt specific, critical personas like a "compliance professional" or a "skeptical VC." This simulates targeted, real-world feedback to pressure-test arguments and reveal blind spots.

Move beyond simple prompts by designing detailed interactions with specific AI personas, like a "critic" or a "big thinker." This allows teams to debate concepts back and forth, transforming AI from a task automator into a true thought partner that amplifies rigor.

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.

After an initial draft is generated, Lieberman's system sends it to an AI "Writer's Council" comprised of personas of famous writers (e.g., David Perel, Morgan Housel). Each persona scores the content from 1-10. If the aggregate score is below a 9, the system automatically triggers a revision loop until the quality threshold is met.

Leverage AI to gain external perspectives without meetings. Prompt it to act as a specific persona—like a skeptical CEO, an enthusiastic user, or a New York Times reviewer—to critique your work. This reveals blind spots and strengthens your idea before sharing it.