AI as Writing Mentor represents a paradigm shift from traditional prompt-based interactions with Large Language Models (LLMs) to a question-based approach where artificial intelligence guides users through their own thinking and writing processes. Developed by Steve Hargadon, this methodology positions AI not as a content generator, but as an intellectual partner that helps users discover and articulate their existing knowledge through structured dialogue.

Conceptual Foundation

The approach emerged from Hargadon's belief that "we learn more naturally through conversation and dialogue rather than through traditional information delivery methods." Drawing on his experience conducting "several hundred interviews" over four years for his FutureofEducation.com project, Hargadon observed that interview conversations serve as "an extremely effective way of diving into a topic." He noted that the interview process "doesn't just extract information, it actually helps the guest communicate their ideas in more cogent and immediate ways."

This insight led to what Hargadon describes as "flipping the script entirely" on LLM interactions. Instead of users prompting the AI, the AI interviews the user through systematic questioning. The methodology draws inspiration from what Hargadon references as "an old Irish saying: 'How will I know what I think until I hear myself say it?'" This captures the core principle that "the process of speaking my thoughts out loud in response to questions doesn't just help me communicate what I already know, it actually helps me discover and refine my thinking in real-time."

Problems with Current Approaches

Hargadon identifies two fundamental issues with traditional prompt-based AI interactions. First, there are "real and growing concerns about AI's impact on our thinking abilities," with research suggesting that "overreliance on AI can actually diminish our cognitive skills." When users "constantly let the LLMs do our reasoning or thinking and writing, we risk weakening the very mental muscles that make us effective thinkers, writers, and problem-solvers."

Second, traditional approaches fail to produce authentic output. As Hargadon explains, "traditional prompt-based AI interactions don't produce writing that feels authentic, least of all to ourselves." The resulting content "may cover your topic but doesn't really capture your authentic voice and sometimes not even your actual thinking process."

Methodology and Process

The AI as Writing Mentor approach operates through structured questioning rather than content generation. Hargadon built "a prompt that would tell the large language model how to interact with me in a question-based way." The process becomes particularly natural when conducted through voice chat, making it "very much like an actual interview with a person."

The methodology allows for dynamic interaction where users can "interrupt (which I do frequently) and change wording to actually reflect what I'm thinking." This creates an environment where "the AI isn't generating content for me; it's helping me discover and articulate what I already think about a topic." The resulting output consists of "literally my specific words and thoughts put into writing, just organized and refined through conversation."

Educational Applications

For educators and students, this approach offers what Hargadon terms "an AI form of Socratic teaching." Students can have AI interview them about research topics, "helping them discover what they actually know, identify gaps in their understanding, and then provide help in learning about the areas they need to learn about."

The method addresses concerns about academic integrity by positioning AI as a learning partner rather than a content source. Instead of students using "AI to cheat or bypass their own thinking," they learn to use AI as "an intellectual partner." Teachers can model the process, demonstrating "how thoughtful questioning leads to deeper exploration of subjects, the same principle that makes Socratic dialogue so powerful in the classroom."

Relationship to Human Agency

Within Hargadon's broader framework of AI empowerment, the writing mentor approach exemplifies how AI can enhance rather than replace human capabilities. He positions this as part of AI's role in "turning users into 'agents' of their own ideas, bypassing technical hurdles that once gated achievement."

For individuals who struggle with writing mechanics while possessing valuable insights, AI serves as a bridge to expression. As Hargadon describes from personal experience: "Writing, for me, is like pulling teeth. My ideas flow in conversation, but the page is a battlefield." The AI writing mentor approach allows such individuals to "ramble my thoughts" while the AI "shapes my ideas and language into drafts." Crucially, "the soul of the work, my ideas, and my voice remain mine."

Implications for Human-AI Collaboration

Hargadon positions AI as Writing Mentor within "a fundamental reimagining of how humans and AI can work together." Rather than treating AI as "a sophisticated content generator that we command," the approach reveals AI's "potential as a thinking partner that helps us access our own knowledge and develop our own ideas."

This collaborative model "doesn't just produce better writing

• it actually strengthens our cognitive abilities rather than weakening them." Hargadon suggests this represents a sustainable path forward that moves away from pursuing "artificial general intelligence or artificial superintelligence through large language models" and instead provides "a really good model for how large language models can evolve to help us as humans."

The methodology exemplifies what Hargadon envisions as "the future of productive AI use: not replacement, but a unique intellectual partnership" where AI serves as an amplifier of human agency rather than a substitute for human cognition.