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.

Open Dashboard

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.

Visit shilpiworks.com

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.

When the Agent Decides What Agent to Build — and the Mothers It Couldn't See

A meta-agent in production picked Mother's Day off the calendar and spawned a Mothers Appreciation Sticker Agent on its own — wrote, debugged, and merged its own code. The creator loop works. The audit loop is not optional.

April 24, 2026

Netrii Releases Free Online Dementia Care Guidebook

Understanding Dementia — 15 evidence-based chapters and an interactive knowledge portal with 200+ concepts — is now available for free at netrii.com.

April 13, 2026

Your Database Is Fine — You're Knocking on the Wrong Door

A one-word hostname change fixed two days of intermittent 500 errors. But we spent three hours planning a full provider migration before discovering the answer was in Prisma's own docs the whole time.

April 5, 2026

Your Database Is Fine — The Proxy Isn't: A Prisma Data Platform Outage Story

The Prisma Data Platform proxy went unreachable during a routine deploy. The database was healthy the entire time. Here is what we learned about deprecated middlemen and why ISR caching saved the site.

April 4, 2026

Organic Engagement Loops for an AI Sticker Shop — What We Actually Built

27 AI agents, 600+ stickers, and zero engagement surface. The site architecture was one-directional — agents produced, visitors browsed, nothing flowed back. Here is how we added hearts, shares, a fresh feed, and trending — and why it matters for the context graph.

April 4, 2026

Curation at the Edge: The Strategic Value of Domain-Specific AI Constraints

The ECE agent isn't just generating art; it's automating the curation of a technical canon. By applying domain-specific constraints—circuit-schematic aesthetics and curated pioneer lists—we transform generic generative AI into an authentic practitioner's tool.

April 1, 2026

Engineering Wisdom as a System: From Blueprints to Binaries

Engineering wisdom is a high-entropy dataset. To make it consumable for the Shilpiworks Engineering Collection, we developed a 'Blueprint Technical' visual system that provides a low-entropy interface for complex technical insights.

April 1, 2026

Executive Verdict: The Chat-Based Control Plane is a Systems Trust Boundary

A systems-level diagnosis of using Telegram as a production control plane—balancing operator proximity with trust boundary rigor.

March 31, 2026

Why Generic AI Falls Short for Technical Audiences: Building the ECE Sticker Agent

Generic quote generators produce generic results. When we wanted stickers that actually resonated with electrical and computer engineers, we had to build a dedicated agent with domain-specific visual language—circuit-schematic aesthetics, monospace typography, and a curated canon of EE/CE pioneers from Claude Shannon to Jensen Huang.

March 30, 2026

We Wiped Our Production Database in 90 Minutes: A Prisma Postgres Post-Mortem

A routine analytics feature addition turned into a full production database wipe. Here's how running raw SQL through Prisma Postgres destroyed 590 products, how we recovered from a backup, and the rules we now follow to make sure it never happens again.

February 27, 2026

Two Silent Killers: Vercel Cron Auth and the Two Flavors of OpenAI 429

Five of our eight AI agents silently stopped running for days. The culprit was two separate bugs that looked identical in the logs — one a misconfigured auth header, the other a billing cliff. Here's how we untangled them.

February 25, 2026

Building a 712-Species Wildlife Sticker Machine: Dataset-Driven AI Generation

We took the Minnesota DNR's public dataset of 712 wildlife species and wired it directly into an AI agent. Every day, it picks the next ungenerated species, researches it, generates a dreamy watercolor sticker, and publishes it automatically. Here's what we learned about dataset-driven creative pipelines.

February 23, 2026

The Vercel Edge Cache Trap: Why force-dynamic Doesn't Always Work

We kept adding new stickers to the shop and they wouldn't appear — even after redeploying. The page was serving 8-day-old HTML. We tried everything. Here's the root cause and the one-line fix.

February 23, 2026

We Built an AI That Watches Our AI: The Ops Observer

We have 7 AI agents running 24/7 generating stickers. When they fail silently, we don't know until we check the database manually. So we built an eighth agent whose only job is to watch the other seven — and email us a diagnosis when something goes wrong.

February 23, 2026

When AI Generates Art: The Hidden Challenge of OCR and Transparency

We launched a new autonomous agent to generate Minnesota wildlife stickers every day. Here is what we learned when the AI decided to paint our text instead of writing it.

February 22, 2026

Debugging Mastra: Why Our AI Workflow Silently Ate Errors

We built six specialized AI sticker agents on Mastra workflows. They all silently stopped publishing. Here's the root cause, the debugging expedition, and three rules every Mastra user should know.

February 18, 2026

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.