Private circulation Issue 02

Field Notes

A weekly dispatch from the edges of the knowledge graph.

Week of

Mar 30–Apr 5, 2026

27 sources / 113 insights

Five things worth knowing

1
Eric Siu AI Agents
Deploying Jack Dorsey's AI-Native Organization Blueprint at Single Grain

> Eric Siu describes 4 months of running an AI-native company architecture inspired by Jack Dorsey and Roelof Botha's "From Hierarchy to Intelligence" essay. Maps Dorsey's four layers (Capabilities, World Model, Intelligence Layer, Surfaces) to actual implementation at Single Grain using Mac Mini +

2
hoeem Claude
Mastering Claude Cowork - Complete Guide to Autonomous Task Delegation

> Comprehensive guide to Claude Cowork covering setup, workspace structuring, automation stack (skills, plugins, scheduled tasks, dispatch mode), MCP connectors (Zapier connects 8,000+ apps), browser use, computer use, token management, and masterclass workflows (morning brief, content repurposer, f

3
Nyk Obsidian
Claude + Obsidian: The Three-Layer Memory Stack That Compounds

> Nyk describes a 3-layer memory architecture for Claude + Obsidian that solves context amnesia: Layer 1 (Session Memory via CLAUDE.md + auto-memory directory), Layer 2 (Knowledge Graph via Obsidian vault + MCP bridge with smart-connections and qmd), Layer 3 (Ingestion Pipeline via brain-ingest tool

4
Nick Spisak Obsidian
How to Build Your Second Brain - Step-by-Step Karpathy Method

> Nick Spisak provides a detailed implementation guide for Karpathy's LLM knowledge base approach. Covers the exact folder structure (raw/, wiki/, outputs/), schema file (CLAUDE.md), agent-browser for automated web scraping, wiki compilation workflow, Q&A against accumulated knowledge, and monthly h

5
Ashu Garg AI Agents
Decision Traces as Enterprise Moat - Context Graphs Reshape B2B

> Ashu Garg (Foundation Capital) and partner Jaya Gupta argue that decision traces — structured records of why decisions were made, not just what was decided — are the enterprise equivalent of B2C behavioral data. AI agents create decision checkpoints automatically: every time a human edits an agent