Home

Using AI as a Thinking Partner for Ambiguous Problems

This site documents an ongoing exploration of how AI—specifically large language models—can be used as a thinking partner, not a shortcut.

The focus is on reasoning, conceptual framing, and decision-making in situations where problems are poorly defined, multi-stakeholder, or culturally complex.

This is not a tutorial site, a prompt collection, or an AI productivity blog.

What this is for

This work may be useful if you:

  • Work with ambiguous or underspecified problems

  • Are skeptical of AI hype but curious about real leverage

  • Care about how conclusions are formed, not just what they are

  • Are interested in AI as a cognitive aid, not a replacement for judgment

What this is not

This site is not for:

  • “Best prompt” collections

  • Quick monetization schemes

  • Step-by-step AI how-to guides

  • AI news, reviews, or trend commentary

Those topics are well covered elsewhere.

What you’ll find here

  1. Worked case studies
    Real projects explored step-by-step, including false starts and course corrections.
    (Example: KikiMichi, a long-tail cultural discovery concept.)

  2. Reusable reasoning artifacts
    Needs maps, framing pillars, flow models, and decision scaffolds intended to be adapted by others.

  3. AI interaction patterns
    How conversations with AI are structured to surface assumptions, test coherence, and avoid self-deception.

Why this work is public

This material is shared publicly to test whether AI-assisted reasoning can produce insights that remain valuable outside the conversation in which they were created.

Only material that may be useful to others is published here.
Detailed working notes and exploratory dialogs remain private.

Start here

If you’re new, these pages provide a representative entry point:

  • KikiMichi: Conceptual Framing Overview

  • From Friction to Human Need: A Diagnostic Method

  • Needs → Principles → Framing Pillars

  • Where Existing Platforms Break for Long-Tail Cultural Events

  • How I Use ChatGPT as a Reasoning Partner

(5–7 links max. Stop there.)

About

I am an independent researcher and designer interested in how systems—technical, cultural, and organizational—can be understood and improved under real constraints.

My interest is not AI as a product, but AI as a tool for thinking clearly when problems resist easy definition.

Updates

Selected summaries and pointers are posted on LinkedIn.
Primary work and artifacts live here.