How we think, build, validate, and learn.
A working record of real product questions, decisions, tests, and changes—published without pretending the work is more complete than it is.
Featured story
One question worth following closely
Fiduciary AI Shopping Agents: Why Prompting 70B LLMs Alone Causes False Purchase Refusals
A 50-scenario benchmark of decision models for fiduciary shopping agents — Clef-omni vs Jev vs Strands Decider, and why prompting alone backfires.
Read the storyLatest notes
Recent work from the Lab
Why Did Abbot Fahai Imprison the White Snake? Reconstructing the Philosophy of Boundary and Freedom
Why the Legend of the White Snake is not a fairy-tale demon romance, how we reconstructed Fahai as an austere institutional guardian of boundary rather than a cartoon villain, and why Book 02 resolves the tragic collision between cosmic order and sovereign love.
Generative AI Asset Pipeline: How We Built Drift-Resistant Production IP for Mythic Characters
When exploring visual IP with generative AI, the true bottleneck isn't synthesis speed—it is decision pollution and identity drift. Here is how we adapted version-locking, three-tier directory isolation, and anchor density rules to turn volatile AI generation into a dependable production discipline.
Scaling AI-Generated Codebases: The Flat-4 Architecture (F4A) for Context Window Control
When heavily integrating AI agents, we hit a brutal wall of hallucination and GC micro-stutters. We needed a draconian, highly-deterministic 6-layer architecture to survive >100Hz hardware polling. Today, we open-source it.
Elder Care App UX Design: Why Senior Mode and Family Caregiver Views Must Be Built Separately
Older adults need low-friction actions and unmistakable confirmation. Families need fast understanding, clear priorities, and traceable follow-through. One interface cannot responsibly optimize for both.
The homepage shows a focused editorial selection, not the full archive.
View all 9 articlesAbout the Lab
Different formats. One editorial standard.
We publish what the evidence supports, distinguish observation from inference, and state what remains unresolved.
Rethink
Define the real problem and question why the existing answer is not enough.
Lab Notes
Trace real product work, including failed attempts, supplier feedback, and changed decisions.
Product Breakdown
Examine why a product was designed this way—from trade-offs to business and delivery logic.
Prototype
Show what each hardware, software, 3D, or UX prototype is trying to validate.
Launch
Explain why a product is ready now, who it serves, what was validated, and where its limits remain.