🔟 Top 10 Prompts to Map Yourself to the AI User Population
Here are 10 high-signal prompts designed to help an individual map themselves against the broader population of AI users by comparing behavior, intent, complexity, or output. Each one is crafted to elicit diagnostic insight based on system-wide norms or LLM benchmarking.
DM — me for my results set.
1. “Compare my AI interaction patterns to the median user behavior across the system.”
Measures: session length, prompt recursion, and content type.
Outcome: percentile-based self-awareness.
2. “Classify my usage by complexity: Am I a casual, functional, creative, or meta-strategic user?”
Measures: prompt abstraction, intent layering, role play, long-form reasoning.
Outcome: usage archetype with adjacent personas.
3. “Evaluate how my prompt engineering differs from typical prompts in structure, depth, and goal orientation.”
Measures: syntax variance, recursion depth, goal-exploration.
Outcome: style fingerprinting vs. norm.
4. “Analyze my interaction for intellectual or thematic patterns and compare them to global prompt clusters.”
Measures: topic domains, novelty, and conceptual links.
Outcome: prompt taxonomy location (e.g., productivity vs. philosophy vs. fiction).
5. “Where does my narrative use of AI place me within the community of long-form content creators?”
Measures: serialized storytelling, persona work, coherence.
Outcome: alignment with authors, educators, or analysts.
6. “Quantify my multimodal integration compared to typical users: text, image, code, and voice.”
Measures: modality type and frequency.
Outcome: creative-technological balance index.
7. “Rank my collaborative rhythm — how often I refine, build upon, or repurpose outputs — compared to system averages.”
Measures: turn depth, revision loops, modular reuse.
Outcome: iterative engagement score.
8. “Assess whether I tend to use AI for extraction (utility) or exploration (discovery) more than the median user.”
Measures: directive vs. speculative prompts.
Outcome: extraction-exploration continuum.
9. “Estimate the uniqueness of my prompt style using language fingerprinting against system-level prompt data.”
Measures: entropy, token diversity, stylometric signature.
Outcome: originality percentile + style cohort.
10. “If my usage were plotted on a multidimensional AI capability radar, what would my shape look like?”
Measures: breadth of skills, creativity, abstraction, and domain switching.
Outcome: self-reflective radar chart vs. median template.