Case study
howtothink.ai — a public knowledge graph, built solo, in production.
A live platform demonstrating the same systems thinking, AI-driven content production, and SEO architecture we will apply to your retail or ecommerce operation.
- Atomic lessons
- 1,700
- Phases / sections
- 85 / 9
- SEO FAQ pages
- ~9,700
- Graph edges
- 3,300+
Why a personal-epistemology project matters to a retail buyer
You are not buying lessons on epistemology. You are buying the ability to ship a knowledge-graph-driven content surface in your operation, the discipline to publish under load, and the SEO architecture that compounds over months. howtothink.ai demonstrates each of those skills in production, in public, against a real domain.
What it demonstrates
- Systems thinking. Content modeled as a graph, not a list. Lessons reference prerequisites, enables, and supports. Pages render adjacency so readers move sideways through related concepts.
- AI-driven content production at scale. ~9,700 FAQ pages generated, validated, and deployed via a dedicated pipeline — not pasted from a chat session. Every page has demand scoring (Ahrefs), schema.org markup, and an editorial gate before publish.
- SEO depth. Schema.org JSON-LD on every page, a sitemap that exposes the graph, and an internal linking strategy that compounds topical authority. Same patterns we apply to retail product pages.
- Willingness to ship the same things we recommend. If we tell you to build a content engine that publishes daily, we have built one and run it. If we tell you to wire schema.org across your catalog, we have wired it across 9,700 pages.
Architecture summary
Next.js 16 (App Router) + Tailwind. Upstash Redis + Vector for search and personalization. Knowledge graph generated from markdown source via TypeScript scripts. PostHog for analytics. Vercel for deploy. Auto-deploy on push to main, no manual CLI steps in the deployment loop.
Source code: github.com/cosm-agency/howtothink.