Live
Plugin
A standalone memory runtime for AI agents that separates retrieval, historical recall, temporal validity, current work, trust, decisive selection, traceability, unfinished work, and explicit memory writes from permission to influence present behaviour.
Problem
Long-running AI agents accumulate files, conversations, decisions, failures, instructions and changing project state, but ordinary retrieval cannot tell historical evidence from current guidance, relevant material from authoritative material, or remembered information from permission to act on it.
Outcome
A standalone remembering runtime where canonical project history is retrieved strongly, routed by purpose, interpreted temporally, conditioned on the work being done, gated by standing, reduced to decisive provenance-bearing evidence, recorded in an immutable trace, with unfinished work tracked and explicit memory actions accepted without granting the writer authority over behaviour.
Book: Memory From First Principles
Capstone: The Memory From First Principles application: a real coding-agent plugin implementing the book’s earned path from canonical project history through retrieval, routing, temporal state, safe framing, trust, decisive selection, durable traces, open loops, and explicit memory actions.
Live
Application
Move beyond isolated prompts into reusable techniques, composed workflows and working sessions.
Problem
Isolated prompts are hard to reuse, compare and improve.
Outcome
A library of reusable prompt techniques, workflows and recorded sessions.
Book: Freestyle Cognition
Live
System
Evidence-first AI systems where claims, decisions, policy boundaries, failure states and replay remain explicit.
Problem
AI systems can cross from model output into decisions and actions without preserving the evidence, claim boundaries and policy state needed to audit or replay them.
Outcome
A bounded decision system whose important claims, evidence, decisions, failures and replay state remain explicit across runtime boundaries.
Live
Runtime
A relation-aware embedding runtime that measures identity, compatibility, preservation, and policy-scoped usability instead of trusting raw vector similarity.
Problem
Embedding systems often treat proximity as permission: if two vectors are close, the application behaves as though meaning, equivalence, compatibility, or preservation has been established.
Outcome
A measured runtime that records space identity, evaluates geometry and transformations, preserves evidence, and grants usability only for scopes that passed declared tests.
Book: Embeddings From First Principles
Capstone: RELATE 1.0: the embedding runtime, corpus, benchmarks, preservation profiles, and replayable evidence behind the book.
Live
Runtime
A durable runtime for putting model intelligence inside an inspectable process with explicit state, authority, effects, verification, acceptance, replay, and deterministic next-operation policy.
Problem
A model call can produce useful intelligence without producing a reliable process: chat history hides state, successful requests are confused with completed work, model claims become evidence, retries repeat side effects, and the system has no durable answer to what should happen next.
Outcome
A runtime where stochastic cognition is bounded by deterministic state projection, explicit authority, preserved observations, verification, acceptance, replay, and a recorded policy for choosing the next operation.
Book: Applied AI
Capstone: The Applied AI capstone: one task carried from directive and context through model cognition, controlled effect, bound verification, acceptance, replay, and an audit of the joints between them.
Live
Toolkit
Small, focused applications that wrap useful AI workflows in an accessible interface.
Problem
Ideas from the books need a concrete place to be tried on real tasks.
Outcome
A toolkit that turns book ideas into research, planning, writing and building workflows.
Book: Applied AI
Reference
Workflow
An offline Pi coding-agent capstone that turns a parser bug into a reviewable patch with reproduced failures, host verification, source references and a human review dossier.
Problem
A coding agent can propose a plausible fix without establishing that it reproduced the bug, respected file permissions, preserved existing behavior or completed the checks.
Outcome
A proposed patch accompanied by recorded test results, validated source references and a review dossier, with the original fixture unchanged and acceptance left to a person.
Book: Pi Agents: Building on the Coding Agent
Capstone: An end-to-end parser repair: reproduce the failure, inspect source, edit a disposable copy, run independent host checks, and produce a patch and evidence dossier.
Building
Experiment
Experiments and practical patterns for local models, browser-native tools and user-controlled AI.
Problem
Browser-native AI needs patterns for capability, safety and user control that don't exist yet.
Outcome
Tested patterns for local models, observability, tooling, security and personal policy.
Book: Browser AI From First Principles
Building
Tool
A user-owned browser AI layer that can filter, amplify, search, organize and act on information while keeping context, provenance and authority inspectable.
Problem
The browser contains the user’s real information environment, but today context is fragmented across pages, tabs, messages and services while AI assistance is usually trapped inside isolated provider interfaces.
Outcome
A user-controlled browser layer that can find, filter, amplify, retain and act on information using explicit policies, typed tools and inspectable evidence.
Book: Browser AI From First Principles
Capstone: A user-owned browser AI coordinator and Digital Lens built on the Browser AI Observatory, typed tools and explicit authority boundaries.