Built by Us
We don't just advise. We build and operate real AI systems in production. These are our proof points — the working systems that keep our expertise sharp and operating-grade.
Dementia Liquid Learning
Knowledge that flows where care is needed.
Dementia Liquid Learning is an AI-generated intelligent textbook and knowledge portal for understanding dementia and cognitive decline. Built with a 200-concept learning graph, 15 comprehensive chapters, and interactive simulations, it transforms complex medical knowledge into accessible, structured learning.
The platform combines a care guidebook with an interactive knowledge portal, a community bulletin board, and AI-powered Q&A — making evidence-based dementia education available to caregivers, families, and healthcare professionals.
Built using Dan McCreary’s intelligent textbook methodology with MkDocs Material, the project demonstrates how AI can generate, validate, and structure educational content at scale while maintaining clinical accuracy and compassionate tone.
How It Teaches
An intelligent textbook architecture that adapts complex medical knowledge into structured, compassionate learning.
200-Concept Learning Graph
A validated directed acyclic graph of 200 concepts across 12 taxonomy categories, with dependency chains ensuring prerequisite-aware learning paths.
15-Chapter Interactive Textbook
Comprehensive chapters with quizzes, references, and interactive MicroSims — all AI-generated at 9th-10th grade reading level with Bloom’s Taxonomy alignment.
AI-Assisted Q&A
Ask questions about dementia care, symptoms, and treatments. Answers grounded in the textbook’s evidence-based content.
Evidence-Based Care Guidebook
Structured pathways through diagnosis, behavior management, therapeutic interventions, safety modifications, and legal planning.
shilpiworks
Human imagination. Machine precision.
shilpiworks is an AI-powered creative commerce platform where 16+ autonomous agents continuously generate, validate, price, and publish wisdom stickers, bookmarks, and laser-cut art. The entire pipeline — from theme selection through image generation, OCR validation, and smart pricing to auto-publish — runs on production cron schedules without human intervention.
Built on Next.js, Prisma, Vercel Postgres, and the Mastra agent framework, shilpiworks is a living laboratory for the same AI agent patterns we advise clients on: multi-model orchestration, decision-trace capture, outcome linking, and autonomous operations at scale.
The stickers themselves are “wisdom stickers for readers, leaders, and lifelong learners” — drawing from philosophy, science, literature, indigenous knowledge, and culture. Thirteen curated collections span themes from Stoic philosophy to curious kids to Minnesota wildlife.
What Makes It Work
The technical architecture behind shilpiworks reflects the same patterns we help clients design and deploy.
16+ Autonomous Agents
Themed AI agents (Stoic philosophy, Indigenous wisdom, Science, Women of Wisdom, and more) running on production cron schedules — zero human designers.
Multi-Model AI Pipeline
Gemini 2.0 Flash for speed and cost, GPT-Image-1 for generation, with intelligent fallback and cost optimization across models.
Decision Trace Capture
Every agent run logs its full reasoning chain — theme candidates, style selection, OCR attempts, quality scores. Institutional memory, not black boxes.
Outcome Linking
Agent decisions are connected to product performance — page views, cart adds, purchases, and revenue. The system learns what works.
OCR Validation Pipeline
Text legibility is verified before publishing. Failed stickers are auto-retried with corrections — no broken products reach customers.
Perceptual Hashing
Near-duplicate detection prevents the agent network from repeating itself. Theme diversity is tracked and enforced across all agents.
Wisdom Dispatches
The engineering stories behind what we build, told through blog posts as we go.
The same patterns, applied to your business
The architecture, experiment design, and operating integration we use in our own products is what we help clients build. The lessons from operating feed directly into the advice we give.