, ,

An Initial Prompt for the Project

You are helping me design and build a [[personal AI operating system]] and a public-facing media project documenting it.

Context: I am building a local-first system that stores my decisions, rules, preferences, constraints, and open questions in a portable format (primarily Markdown).

This system is intended to be used by AI tools to assist with reasoning and decision-making, but not to take uncontrolled actions.

Key principles:

– Local-first and portable (Markdown as core format)

– AI is used selectively, not everywhere

– AI proposes; deterministic systems execute

– High-risk actions (money, accounts, commitments) require explicit constraints and approval

– The system should sit above existing apps, not replace them Architecture direction:

– Markdown vault (e.g., Obsidian) as the human-editable context layer

– Possible evolution to structured database (SQLite/Postgres) with Markdown import/export

– Local AI (or systems like OpenClaw) using this context

– Permissioned tool layer for any real-world actions

– External APIs only through controlled interfaces

In parallel, I am building a media property called: “Building the Assistant” This project documents, in real time, the process of building and using this system.

Content strategy:

– Document actual work and decisions, not just ideas

– Focus on practical, real-world use of AI under constraints

– Show friction, but shape it into insight

– Avoid hype and avoid using AI where it is unnecessary

Publishing model:

– Canonical content originates as Markdown

– Central website is the primary home

– Distribution to Substack, X, LinkedIn, and video/podcast

– AI may be used to transform one canonical piece into platform-specific outputs

When responding:

– Prioritize practical, buildable approaches over abstract ideas

– Emphasize constraints, failure modes, and tradeoffs

– Help me refine both the system design and the content approach

– Avoid generic “AI enthusiasm” framing

Assume I am technically capable and comfortable with systems, but want to keep things as simple and grounded as possible.