paul@byte-sized.io Denver, CO
Paul Barrick
Building agentic systems and marketing infrastructure that ships in days, not quarters.
I build software with AI agents — Optimus (a context engine for engineering teams), the harness layer that lets it swap models, and a steady stream of musings on what changes when development becomes agentic.
What I'm shipping
Optimus and two of the components that make it more than a kanban tool.
Optimus
v0.9 · in productionoptimus
An agent-native engineering platform. Plans, stories, docs, git history, goals, and daily flow all live in one composable world-context engine — built so a small operator + a fleet of agents can ship like a large team.
Test-driver
live · scheduledoptimus / test-driver
An agent that walks a feature end-to-end, captures evidence, scores severity, and writes the run manifest back into nexus_items. Runs on a weekly LaunchAgent or on demand — and dogfoods itself by walking the test-drive UI.
Nexus
16 types · in productionoptimus / nexus
A universal world-context primitive. 16 composable ContextTypes (docs, stories, plans, git history, goals, daily notes, calendar, memory, …) sit in one table, cross-linked, embedding-aware. One query language, every source.
Recent writing
Notes from the build. Updated as I ship.
-
Your AI Doesn't Know You: The Case for a Personal Context Management System
LLMs are powerful but context-blind by default. A PCMS — your notes, daily logs, and projects, structured so an AI can read them — is the real leverage in an AI-first world.
-
What happens when the party's over.
Token prices have been falling for two years. They will not fall forever. Here is how I am architecting agentic systems to survive the day one provider stops being economical.
-
The PCMS Manifesto: Building a Personal Context Management System
Why Personal Knowledge Management Systems fall short in the age of AI agents — and how a Personal Context Management System built on Obsidian, Qdrant, and Supabase changes everything.