Practical applications, tools and experiments built from the ideas developed in the books.
Books explain the system. These entry points help you use it.
Understand the current technique, mechanism, evidence and failure modes.
Turn the argument into a complete implementation that can be tested.
Package the result around a real problem and a concrete outcome.
Keep the implementation, experiments and evidence inspectable.
Each page keeps the problem, underlying mechanism, implementation and source material connected.
Move beyond isolated prompts into reusable techniques, composed workflows and working sessions.
Small, focused applications that wrap useful AI workflows in an accessible interface.
Experiments and practical patterns for local models, browser-native tools and user-controlled AI.
Browse the solution library by domain. Each solution page connects a real problem to its mechanism, implementation and supporting evidence.
Experiments and practical patterns for local models, browser-native tools and user-controlled AI.
An embedding runtime that knows its own limits: representation, similarity, retrieval, calibration and alignment with measured trust conditions.
Turn language-model behavior into an experimental variable: compiled programs, independent metrics and promotion rules that justify replacing what already works.
Move beyond isolated prompts into reusable techniques, composed workflows and working sessions.
Small, focused applications that wrap useful AI workflows in an accessible interface.