# Your Digital Commander Shepard

> One shepherd to rule them all

A field manual for governing AI agents – philosophy, architecture, and practice.

## The Manifesto

Five tenets. No negotiation.

### I. Statute is Law
Agents don't improvise. They execute written rules – or they escalate. The Statute is the authoritative description of how work is done. Not a suggestion. Not a guideline. Law. The rules evolve – every serious failure updates the Statute – but they are always written down.

### II. The Human Commands
One human owns every decision. Agents propose, execute, review – they never decide. Agents operate inside narrow Rules of Engagement. They do not redefine goals, values, or strategy. The human is accountable for every material action performed by agents.

### III. Own Your Stack
Your data stays yours. Knowledge Lake lives in a git repo you control – not in someone else's SaaS. Observability runs on open-source – OpenTelemetry, Prometheus, Grafana – not on a Datadog invoice. Local models where it makes sense. What goes to the cloud stops being yours. Open-source. Self-hosted. Sovereign.

### IV. The Eye Sees Everything
Every agent action is logged. Every tool is a named gate with a risk level and a paper trail. Read-only by default – mutations require explicit Statute and human approval. You cannot command what you cannot see.

### V. Small and Sharp
Capability is modular. Each skill is scoped, testable, and replaceable. Complex workflows are compositions of small skills, not monolithic mega-agents.

## Key Concepts

- **Shepherd** – the human commander; strategic decisions, oversight, final authority
- **Staff** – the instrument of control; rules, constraints, directives
- **Pasture** – the bounded environment where agents operate
- **Gates** – entry and exit points; what flows in, what flows out
- **Memory** – what the herd remembers across sessions
- **Eye** – observability; the shepherd sees everything

## Topics

- AI governance frameworks and agent oversight
- Human-in-the-loop architectures
- Automation with guardrails
- The shepherd metaphor as governance model

## Articles

- git commit -m 'init': The first dispatch. Why this blog exists, and what the shepherd sees from the hilltop. https://digitalshepard.ai/articles/init/
- Fear and Loathing in the Gas Town: The AI gold rush ate the hardware. The hardware ate the power grid. Nobody is driving. https://digitalshepard.ai/articles/fear-and-loathing-in-the-gas-town/
- Vibe Coding Apocalypse: Moltbook exposed 1.5M tokens in 5 days. OpenClaw spawned a $16M crypto scam. Inside the vibe coding catastrophe – and why the hangover is just beginning. https://digitalshepard.ai/articles/vibe-coding-apocalypse/
- The Eye: You cannot command what you cannot see. Inside the shepherd's eye – three signals, four questions, and an open-source stack that changes everything. https://digitalshepard.ai/articles/the-eye/
- Faith-Based Arithmetic: $143 billion in losses before the first profit. $1.4 trillion in infrastructure deals. The AI industry's math doesn't add up – and everyone knows it. https://digitalshepard.ai/articles/faith-based-arithmetic/
- The Eye, Part 2 – Wiring: Clone a repo, run docker-compose, see eight dashboards in ten minutes. Three AI CLIs, one observability stack, zero Python. The Eye, deployed. https://digitalshepard.ai/articles/the-eye-part2/

## Links

- Website: https://digitalshepard.ai
- Articles: https://digitalshepard.ai/articles
- Manifesto: https://digitalshepard.ai/manifesto
- About: https://digitalshepard.ai/about
- Tags: https://digitalshepard.ai/tags
- Archive: https://digitalshepard.ai/archive
- RSS Feed: https://digitalshepard.ai/feed.xml
- GitHub: https://github.com/shepard-system

## Author

Shepard – Data & Platform Engineer, AI Governance